Neuro Computing Publications

publications
Article
A Scientometric Study of Neurocomputing
Publications (1992–2018): An Aerial Overview of
Intrinsic Structure
Manvendra Janmaijaya 1 , Amit K. Shukla 1 , Ajith Abraham 2 and Pranab K. Muhuri 1, * ID
1 Department of Computer Science, South Asian University, New Delhi 110021, India;
manvendra995@gmail.com (M.J.); amitkshukla@live.com (A.K.S.)
2 Machine Intelligence Research Labs (MIR Labs), 3rd Street NW, P.O. Box 2259, Auburn, WA 98071, USA;
ajith.abraham@ieee.org
* Correspondence: pranabmuhuri@cs.sau.ac.in

Received: 11 May 2018; Accepted: 16 July 2018; Published: 19 July 2018
Abstract: The international journal of neurocomputing (NC) is considered to be one of the most
sought out journals in the computer science research fraternity. In this paper, an extensive bibliometric
overview of this journal is performed. The bibliometric data is extracted from the Web of Science (WoS)
repository. The main objective of this study is to reveal internal structures and hidden inferences,
such as highly productive and influential authors, most contributing countries, top institutions,
collaborating authors, and so on. The CiteSpace and VOS viewer is used to visualize the graphical
mapping of the bibliometric data. Further, the document co-citations network, cluster detection and
references with strong citation burst is analyzed to reveal the intellectual base of NC publications.
Keywords: neurocomputing; bibliometric study; scientometric mapping; co-citation analysis; Web

of Science
1. Introduction
Bibliometrics (also referred as Scientometrics) as a research area has received tremendous attention
from the scientific fraternity in recent times [1]. Bibliometrics is identified as an efficient technique to
build a general outline of a certain scientific research field. There has been a rapid development in
the field of bibliometrics in recent times attributing to social developments significantly gaining from
the advancement of the internet and computers [2]. Scientometrics therefore gives an aerial view of
scientific activity. It basically is a part of library and information science, but it has been judiciously
used in numerous other research areas like management [3,4], energy & fuels [5,6], psychology [7,8],
Dielectric and bioimpedance research [9], Selfish memes [10], and so on. Bibliometric study is not only
celebrated in the field of computer science but is also finding increasing attention in domains such as
decision support systems [11,12], bioinformatics [13,14], heuristics [15], big data [16–18], and software
engineering [19]. Moreover, there has been a quality scientometric research work contribution in last
few years, such as Fuzzy decision making [20], fuzzy theory research in China [21], Real-time operating
systems [22], Linguistic decision making studies [23], Ordered weighted averaging operators [24],
and Atanassov intuitionistic fuzzy sets [25].
Apart from subject specific bibliometric study, there are several journal specific studies, such as
Knowledge Based Systems (KBS) [26], International Journal of Intelligent Systems (IJIS) [27], IEEE
Transactions on Fuzzy Systems (TFS) [28], European Journal of Operations Research (EJOR) [29],
Computers & Industrial Engineering [30], Information Sciences (INS) 1968–2016 [31,32], Medicine [33],
Applied Soft Computing [34], and others [35–38].
Publications 2018, 6, 32; doi:10.3390/publications6030032 www.mdpi.com/journal/publications

Publications 2018, 6, 32 2 of 22
Neurocomputing (NC) is one of the most pioneering journals in the field of neurocomputing.
Throughout the years it has maintained a high reputation and is widely read by the computer science
research fraternity. NC publishes various document types, such as articles, theoretical contributions,
literature reviews, conference and workshop meeting reports, short communications, and so on.
All these document types cover a wide area of computer science discipline including signal processing,
speech processing, image processing, computer vision, control, robotics, optimization, scheduling,
resource allocation, and financial forecasting. NC not only covers the theoretical aspects but also
focuses on the practical contributions, such as simulation software environments, emulation hardware
architectures, models of concurrent computation, neurocomputers, and neurochips (digital, analog,
optical, and biodevices) [39]. The popularity of NC journal can be observed from the impact factor
this journal has acquired in such short span of time. Impact factor (IF) is the measure of the frequency
with which an article of the journal is cited in year. It is a journal metric used for analyzing the rank of
a journal. According to the latest Journal Citation Reports of the Web of Science, which is owned by
Clarivate Analytics, NC journal has an impact factor of 3.317.
The major contribution of this paper are as follows:
1. This paper reports a detailed study of the generic bibliometric impression of the journal
of NC publications by examining the most prominent articles, institutions, authors, author
collaborations, institute collaborations, country collaborations, etc.
2. The purpose of this study is to provide an intrinsic structure of NC publications and the targeted
research areas where the contributions are made.
3. A detailed study of the NC publication base is also performed to understand the knowledge base
of NC publications.
4. The top cited articles in this journal are listed to give highlights of the NC publications.
5. The data of all the documents considered for this study have been retrieved from the Web of
Science (WoS) database which comprises of several document types, such as articles, proceeding
papers, letters, editorials, and reviews.
6. Statistical techniques and analysis determines the nature of the NC citations and their structure.
The paper is organized as follows: Section 2 explains the data collection methodology, performance
indicators, and the visualization tools used in this paper. In Section 3, we have covered the
publications and citation structure, most productive and influential authors, top ranked countries
in NC, and the best institutions contribution in NC. The visualization of the publication structure
of the various entities (authors, countries, institutions, etc.) is shown with the help of the Citespace.
Then we have explained the bibliometric landscape and included the document co-citation analysis in
Sections 4 and 5, simultaneously. Finally, a conclusion is drawn in Section 6 followed by the references
used in this paper.
2. Methodology and Performance Indicators

The repository of Web of Science (WoS) is utilized for this study, which is a scientific citation
indexing service maintained by Clarivate Analytics. WoS is the first multidisciplinary bibliographic
index of journal publications designed. It is considered a standard data source for bibliometrics.
Other databases such as Scopus by Elsevier are also used by bibliometricians. The first volume of
NC came in the year 1989, however, the data for this study has been extracted from WoS where NC’s
publications are from the year 1992. Therefore the data span of this study is from 1992 to 2018. The data
was collected in December 2017. A total of 10,838 publications were retrieved for the above said period.
The query used in the search engine of WoS was “SO = Neurocomputing”. Each record of the data
retrieved from WoS comprises a number of fields such as author, author affiliation, title, abstract,
citations record, and so on.
This study uses a range of scientometric indicators combined with statistical analysis and
visualizations tools. Associations between several entitles/variables (author, organization, or country)
have been explored, which are defined as follows:
(i) Co-citation analysis: This is another way to analyze the citation structure and provides a glimpse
of the relationships between papers, and through them other entities, inside a research domain.
It basically tells us that if two entities are co-cited, i.e., cited together more frequently then there
are closer academic or disciplinary ties between them.
(ii) Bibliographic coupling: This is the opposite of co-citation, it is the number of times two or more
entities cite the same entity. Both co-citation and bibliographic coupling indicate disciplinary
links. The number of co-authored documents identifies collaborative or co-authorship links
between two entities, directly linking authors, institutions, or countries. (By entity we mean
either an author, an organization, or a country.)
(iii) Document co-citation analysis (DCA): This explores the citation base of publications giving an
insight into the inspiration corpus.
Performance Indicators and Visual Tools: Now, we explain the various scientometric indicators
used for the analysis.
(i) Total Papers (TP)—the total number of papers from a particular source,
(ii) Total Citations (TC)—the total number of citations generated by a particular publication within
the database of WoS.
(iii) Citations per Paper (CPP)—TP divided by TC,
(iv) Hirsch index or h-index—This is equal to the number of papers (N) of an entity that has more
than N citations each [40].
Further, two of the widely used graphical mapping software’s are used, namely, VOSviewer
and CiteSpace
(i) VOSviewer is a tool for generation and visualization of bibliographic networks. It has been used
here for depicting bibliographic coupling and co-authorship between different entities VOSviewer
can be used to construct networks of scientific publications, scientific journals, researchers,
research organizations, countries, keywords, or terms. Items in VOSviewer are visualized in
terms of nodes and edges connecting theses nodes. Items in these networks can be connected
by co-authorship, co-occurrence, citation, bibliographic coupling, or co-citation links. Examples
are bibliographic coupling links between publications, co-authorship links between researchers,
and co-occurrence links between terms. Vosviewer version 1.6.5 has been used for this study.
(ii) CiteSpace [41] has also been used here for visualization and analysis document co-citation of NC
publications. It is an open source Java application used for visualizing trends from metadata of
scientific literature. Citespace version 5.0 R4 SE has been used for this study.
3. Citation Structure of NC Publications

In the year 1992, NC published 29 research articles. Since 1998, the number of publications never
dropped below 100 and the trends of publications are mostly in the increasing order. The maximum
number of 1840 articles were published in the year 2016. The years from 2015–2017 account for
approximately 40% of the total NC publications. In the year 2017, there were 1118 publications up
to the month of November, when the search query was performed, and this count will certainly
increase. For 2018, 143 papers are already included in NC. There is a strong possibility that the journal
is expected to follow the current increasing trend over the years to come.
Figure 1 shows the distribution of citations of NC publications over the years (1992–2018),
which received a total of 106,536 citations. Interestingly, the year 1992 reflects only 30 citations with a
total of 29 publications. The year 1998 accounted for a citation count of 3361 with only 108 publications,
making this the year with the maximum citations per year. However, the maximum number of citations
were attracted in the year 2015, with a total count of 9108. The TC is not shown for 2018 as counting
Publications 2018, 6, x FOR PEER REVIEW 4 of 21
is yet to start. Moreover, the year 2006, with 335 publications, attracted comparable citations (7617)
to that which
Publications 2016
2018, 6, x publications did. On further analysis, this is found to be because of the article
FOR PEER REVIEW 4 of 21by
article by Huang et al. [31] where extreme machine learning is presented along with its theory and
Huang et al.
applications. [31] where extreme machine learning is presented along with its theory and applications.
article by Huang et al. [31] where extreme machine learning is presented along with its theory and
applications.
18401840
Total Publications
Total Publications
13011301
11181118
902 902
702 702
427 427
414 414
393 393
369 369
345 345
342 342
335 335
308 308
295 295
2 0 0 21 0 0 1 257 257
255 255
252 252
2 0 0 20 0 0 0 219 219
1 9 9 19 9 9 9 184 184
143 143
1 9 9 18 9 9 8 108 108
1 9 9 16 9 9 6 103 103
1 9 9 17 9 9 774 74
1 9 9 15 9 9 562 62
1 9 9 14 9 9 439 39
1 9 9 12 9 9 229 29
1 9 9 13 9 9 322 22
2 0 02 0 0 2
2 0 0 23 0 0 3
2 0 0 24 0 0 4
2 0 0 25 0 0 5
2 0 0 26 0 0 6
2 0 0 27 0 0 7
2 0 0 28 0 0 8
2 0 0 29 0 0 9
2 0 1 20 0 1 0
2 0 1 21 0 1 1
2 0 12 0 1 2
2 0 1 23 0 1 3
2 0 1 24 0 1 4
2 0 1 25 0 1 5
2 0 1 26 0 1 6
2 0 1 27 0 1 7
2 0 1 28 0 1 8
Years
Years
Figure 1. Neurocomputing (NC) publications/year distribution.
The diversity in the total number of citations with respect to the total number of publications
overThethediversity
years isin the total
shown number
in Figure of citations
2. There with
has been respect to
a gradual the total
increase in number of publications
the citations over the year. over
The diversity in the total number of citations with respect to the total number of publications
theItyears
is at aismaximum
shown in Figure
in 19982.withThere has been
a value a gradual
of 31.21 as sevenincrease in the citations
publications over the
have attracted more year.
thanIt is
100at a
over the years is shown in Figure 2. There has been a gradual increase in the citations over the year.
maximum
citations in up1998
to thewith
dateathatvalue
dataof was
31.21 as seven
collected forpublications
this study. Ithave attracted
is followed more
by the than 100 citations
publications in the
It is at a maximum in 1998 with a value of 31.21 as seven publications have attracted more than 100
years
to the2006
upcitations and
date 2003 with
that CPP of 22.7 and
for 21.5,
this respectively. This can also be attributed to theinfact that
up to thedata
date was collected
that data was collected study.
for this It is followed
study. by the
It is followed bypublications
the publications the
in years
the
2006a lot of 2003
and publications
with CPPin these
of years
22.7 and have
21.5,attracted a goodThis
respectively. number
can of citations.
also be However,
attributed to the citations
fact that a
years 2006 and 2003 with CPP of 22.7 and 21.5, respectively. This can also be attributed to the fact that
lotaper year count has
oflotpublications
of publications indegraded
these
in these
in the
years have
years
lastattracted
have
few yearsa as shown in Figure
attracted agood
goodnumber
number of
3. This can
citations.
of citations.
possibly be
However,
However, the
the
because
citations
citations
publications
perperyear count in
hasthe later
degraded years
in are
the fairly
last new
few and
years possibly
as shown will
in attract
Figure more
3. Thiscitations
can in
possibly the betimes to
because
year count has degraded in the last few years as shown in Figure 3. This can possibly be because
come.
publications ininthe
publications thelater
lateryears
years are fairly new
are fairly newandandpossibly
possibly will
will attract
attract moremore citations
citations in thein times
the times
to
to come.
Total Citations
91089108
84608460
81688168
Total Citations
76177617
72537253
70857085
58315831
58155815
57175717
55925592
53995399
54295429
43274327
38023802
33613361
30753075
22332233
21862186
17361736
1 9 9 16 9 9 6 14071407
1 9 9 17 9 9 7 982 982
1 9 9 14 9 9 4 516 516
1 9 9 15 9 9 5 765 765
2 0 1 27 0 1 7462 462
3 180
2 30
1 9 9 13 9 9180
1 9 9 12 9 930
1 9 9 18 9 9 8
1 9 9 19 9 9 9
2 0 0 20 0 0 0
2 0 0 21 0 0 1
2002002
2 0 0 23 0 0 3
2 0 0 24 0 0 4
2 0 0 25 0 0 5
2 0 0 26 0 0 6
2 0 0 27 0 0 7
2 0 0 28 0 0 8
2 0 0 29 0 0 9
2 0 1 20 0 1 0
2 0 1 21 0 1 1
2012012
2 0 1 23 0 1 3
2 0 1 24 0 1 4
2 0 1 25 0 1 5
2 0 1 26 0 1 6
Years
Yearsof NC over the years.
Figure 2. Citations structure
Figure 2. Citations structure of NC over the years.

Figure 2.
Table 1 displays the general Citations
citation structure
structure of NC
of NC over the years.
publications from 1992 to 2018. Here, ‘%’ is
used to represent the percentage. There are 16 papers which received more than 200 citations, which
Table 1 displays the general citation structure of NC publications from 1992 to 2018. Here, ‘%’ is
is 0.14% of the total NC publications. With more than 100 citations, we have 56 publications which
used to represent the percentage. There are 16 papers which received more than 200 citations, which
account for 0.51% of total publications. There are 2146 papers with no citations at all, which is 19.8%
is 0.14% of the total NC publications. With more than 100 citations, we have 56 publications which
of total publications. Approximately 80% of the publications had at least 1 citation; among them, a
account for 0.51% of total publications. There are 2146 papers with no citations at all, which is 19.8%
of total publications. Approximately 80% of the publications had at least 1 citation; among them, a
major chunk was published in the last five years and thus this number is bound to change as they are
fairly young
Publications 2018, 6,publications.
32 The year 1998 stands at the top position with the CPP. Almost 50% of NC
5 of 22
publications have attracted more than five citations which indicates the reach of the journal.
35 Citations Per Year

30
25
20
15
10
5
0
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
Years
Figure 3. Citations per year of the NC computing.

Figure 3. Citations per year of the NC computing.
Table 1. General citation Structure in the Journal: NC (1992–2018).
Table
Year
1 displays
≥200
the general
≥100 ≥50
citation
≥20
structure
≥10
of NC ≥1publications
≥5 0
from
TP
1992 to 2018.
h-Index TC
Here, CPP
‘%’ is
used to represent
2018 0 the percentage.
0 0 There0 are 16 0 papers 0 which 0 received
143 more
143 than 200 0 citations,
0 which
0.00 is
2017 0 0 0 1 4 9 264 854 1118 7 510 0.46
0.14%2016of the total0
NC0 publications.
3 21
With more
93
than
419
100
1389
citations,
451
we1840
have 5620 publications
5813
which
3.16
account2015for 0.51% 0 of total
0 publications.
1 73 There 322 are 715
2146 papers
1200 with
101 no1301 citations27at all, which
9190 is 19.8%
7.06
2014 0 1 8 106 321 576 845 57 902 31 8495 9.42
of total
2013
publications.
0
Approximately
2 13 115
80%296of the468 publications
663
had
39
at 702
least 1 citation;
35
among
8200
them,
11.68
a major2012chunk0was published 0 14in the89 last five207 years296and thus398 this29number 427 is bound 36 to change
5826 as they
13.64
2011 1 1 20 91 189 260 350 19 369
are fairly
2010
young 1
publications.
2 19
The year
94
1998187
stands
261
at the
329
top position
16
with the33
345 36
5605
CPP. Almost
5840
15.19
50% of
16.93
NC publications
2009 0 have 2attracted 27 more 124than five
235 citations
313 which
389 indicates
25 414the reach 41 of the 7095journal.
17.14
2008 1 7 30 115 199 277 367 26 393 40 7261 18.48
Neurocomputing
2007 1 4
journal 24
has been
75
publishing
151 227
quality
322
and impactful
20 342
research
35
articles
5405
since
15.80
its
induction.
2006 Table1 2 displays
3 a16list of 82top 40153 most cited
219 articles
305 as30 indexed335 by WoS. 35 All7627
the papers
22.77 in
2005 1 4 17 53 97 154 233 22 255 32 3806 14.93
this list
2004
got more 0
than 0100 citations.
8
Huang
46
et al. [42]
104 161
received
261
the34
highest
295
citations
27
of 2762
3077
since
10.43
2006
for the2003
paper titled
4 “Extreme
9 learning
21 57machine:92 Theory131 and210 applications”.
42 It has received
252 33 citations
5439 21.58with
2002 2 5 11 47 102 162 257 51 308 31 4331 14.06
increasing
2001
speed 1
and has1
a count
6
of 230.17
30
citations
67 108
per year,
230
which27
is highest
257
in 22
the top223440 list 8.69
of most
cited publications.
2000 0 This2 research10 article27 proposed
56 a97 novel185learning 34 algorithm
219 for
24 single2193
feed forward
10.01
1999 0 1 5 25 47 82 162 22 184 24 1737 9.44
neural1998networks 2
where7
the hidden
17 40
nodes58are randomly79 96
chosen 12
and108the weights 30
are
3365
analytically
31.16
assigned.
1997 The0 second1 position 3 is acquired
17 26by paper 39 “Time
59 series
15 forecasting
74 using
18 a hybrid
982 ARIMA
13.27
1996 1 1 8 21 34 47 69 34 103 20 1407 13.66
and neural
1995
network
0
model”
1
authored
3
by
11
Zhang22
[43] where
31
he
52
proposed
10
a62
hybrid approach
15 765
containing
12.34
autoregressive
1994 0 integrated
2 moving
3 average
7 11and artificial
15 25neural14networks 39 for linear
10 and
516 non-linear
13.23
1993 0 0 1 3 3 9 15 7 22 6 180 8.18
modelling
1992
for forecasting.
0 0
These
0
two1are followed
3
by
9
Suykens
17
et12al. [44], 29
Kim [45], 6
and 106
Kohonen 3.66
[46],
for their
Total papers 16 titles 56as follows:
288 Weighted
1371 least squares
3079 5164 support
8692 vector10,838
2146 machines: robustness and sparse
% 0.14 0.51 2.65 12.64 28.40 47.64 80.19 19.8
approximation; Financial time series forecasting using support vector machines; and The self-organizing map,
respectively. The paper by Suykens et al. [44] proposed a method for obtaining robust estimates for
Neurocomputing journal has been publishing quality and impactful research articles since its
regression
induction. byTable
applying a weighted
2 displays version
a list of top 40 of least
most squares
cited support
articles as indexedvector bymachine
WoS. All(LS-SVM)
the papersalong in
withthis list got more than 100 citations. Huang et al. [42] received the highest citations of 2762 since 2006the
a sparse approximation procedure for weighted and unweighted LS-SVM. Kim [45] examined
feasibility of support
for the paper titled vector
“Extreme machines
learning in financial
machine: forecasting.
Theory KohonenIt [46]
and applications”. has gave
receivedan overview
citations with of the
self-organizing map algorithm, namely, a software for visualizing high
increasing speed and has a count of 230.17 citations per year, which is highest in the top 40 list of dimension data.
There
most arepublications.
cited six papers which This were published
research before 2000,
article proposed with the
a novel rest ofalgorithm
learning them published
for single after 2000.
feed
From
forward neural networks where the hidden nodes are randomly chosen and the weights areare
the last five years, there are two papers which are in the list of top 40 most cited list. They
“A survey on fallassigned.
analytically detection:ThePrinciples
secondand approaches”
position and “Weighted
is acquired by paper “Timeextreme learning
series machine
forecasting using for aimbalance
hybrid
learning” from Mubashir et al. [47] and Zong et al. [48], respectively.
Table 1. General citation Structure in the Journal: NC (1992–2018).
Year ≥200 ≥100 ≥50 ≥20 ≥10 ≥5 ≥1 0 TP h-Index TC CPP

2018 0 0 0 0 0 0 0 143 143 0 0 0.00
2017 0 0 0 1 4 9 264 854 1118 7 510 0.46
2016 0 0 3 21 93 419 1389 451 1840 20 5813 3.16
2015 0 0 1 73 322 715 1200 101 1301 27 9190 7.06
2014 0 1 8 106 321 576 845 57 902 31 8495 9.42
2013 0 2 13 115 296 468 663 39 702 35 8200 11.68
2012 0 0 14 89 207 296 398 29 427 36 5826 13.64
2011 1 1 20 91 189 260 350 19 369 33 5605 15.19
2010 1 2 19 94 187 261 329 16 345 36 5840 16.93
2009 0 2 27 124 235 313 389 25 414 41 7095 17.14
2008 1 7 30 115 199 277 367 26 393 40 7261 18.48
2007 1 4 24 75 151 227 322 20 342 35 5405 15.80
2006 1 3 16 82 153 219 305 30 335 35 7627 22.77
2005 1 4 17 53 97 154 233 22 255 32 3806 14.93
2004 0 0 8 46 104 161 261 34 295 27 3077 10.43
2003 4 9 21 57 92 131 210 42 252 33 5439 21.58
2002 2 5 11 47 102 162 257 51 308 31 4331 14.06
2001 1 1 6 30 67 108 230 27 257 22 2234 8.69
2000 0 2 10 27 56 97 185 34 219 24 2193 10.01
1999 0 1 5 25 47 82 162 22 184 24 1737 9.44
1998 2 7 17 40 58 79 96 12 108 30 3365 31.16
1997 0 1 3 17 26 39 59 15 74 18 982 13.27
1996 1 1 8 21 34 47 69 34 103 20 1407 13.66
1995 0 1 3 11 22 31 52 10 62 15 765 12.34
1994 0 2 3 7 11 15 25 14 39 10 516 13.23
1993 0 0 1 3 3 9 15 7 22 6 180 8.18
1992 0 0 0 1 3 9 17 12 29 6 106 3.66
Total 16 56 288 1371 3079 5164 8692 2146 10,838
% 0.14 0.51 2.65 12.64 28.40 47.64 80.19 19.8
Table 2. Top 40 cited publications in NC.
Rank Title Authors Year TC Citations per Year

1 Extreme learning machine: Theory and applications Huang GB; Zhu QY; Siew CK 2006 2762 230.17
Time series forecasting using a hybrid ARIMA and
2 Zhang GP 2003 660 44.00
neural network model
Weighted least squares support vector machines: Suykens JAK; De Brabanter J;
3 2002 615 38.44
robustness and sparse approximation Lukas L; Vandewalle J
Financial time series forecasting using support
4 Kim KJ 2003 463 30.87
vector machines
5 The self-organizing map Kohonen T 1998 462 23.10
6 Convex incremental extreme learning machine Huang GB; Chen L 2007 454 41.27
Enhanced random search based incremental extreme
7 Huang GB; Chen L 2008 376 37.60
learning machine
Blind separation of convolved mixtures in the
8 Smaragdis P 1998 361 18.05
frequency domain
Optimization method based extreme learning
9 Huang GB; Ding XJ; Zhou HM 2010 335 41.88
machine for classification
Designing a neural network for forecasting financial
10 Kaastra I; Boyd M 1996 322 14.64
and economic time series
11 The support vector machine under test Meyer D; Leisch F; Hornik K 2003 291 19.40
Evaluation of simple performance measures for
12 Duan K; Keerthi SS; Poo AN 2003 280 18.67
tuning SVM hyperparameters
(2D)(2)PCA: Two-directional two-dimensional PCA
13 Zhang DQ; Zhou ZH 2005 265 20.38
for efficient face representation and recognition
Table 2. Cont.
Rank Title Authors Year TC Citations per Year

An approach to blind source separation based on
14 Murata N; Ikeda S; Ziehe A 2001 240 14.12
temporal structure of speech signals
Error-backpropagation in temporally encoded Bohte SM; Kok JN;
15 2002 235 14.69
networks of spiking neurons La Poutre H
Recent advances and trends in visual tracking: Yang HX; Shao L; Zheng F;
16 2011 229 32.71
A review Wang L; Song Z
Modified support vector machines in financial time
17 Tay FEH; Cao LJ 2002 194 12.13
series forecasting
Support vector machines experts for time
18 Cao LJ 2003 192 12.80
series forecasting
A comparison of PCA, KPCA and ICA for Cao LJ; Chua KS; Chong WK;
19 2003 191 12.73
dimensionality reduction in support vector machine Lee HP; Gu QM
Empirical evaluation of the improved Rprop
20 Igel C; Husken M 2003 188 12.53
learning algorithms
Determination of the spread parameter in the Wang WJ; Xu ZB; Lu WZ;
21 2003 186 12.40
Gaussian kernel for classification and regression Zhang XY
22 Evolutionary tuning of multiple SVM parameters Friedrichs F; Igel C 2005 185 14.23
A survey on fall detection: Principles
23 Mubashir M; Shao L; Seed L 2013 174 34.80
and approaches
WEBSOM - Self-organizing maps of Kaski S; Honkela T; Lagus K;
24 1998 169 8.45
document collections Kohonen T
Asymptotic and robust stability of genetic regulatory
25 Ren F; Cao J 2008 168 16.80
networks with time-varying delays
26 Natural Actor-Critic Peters J; Schaal S 2008 167 16.70
Artificial neural networks in hardware A survey of
27 Misra J; Saha I 2010 165 20.63
two decades of progress
Learning And Generalization Characteristics Of The
28 Pao YH; Park GH; Sobajic DJ 1994 163 6.79
Random Vector Functional-Link Net
Schreiber S; Fellous JM;
A new correlation-based measure of spike
29 Whitmer D; Tiesinga P; 2003 158 10.53
timing reliability
Sejnowski TJ
Time-series prediction using a local linear wavelet
30 Chen YH; Yang B; Dong JW 2006 156 13.00
neural network
A fast pruned-extreme learning machine for Rong HJ; Ong YS; Tan AH;
31 2008 154 15.40
classification problem Zhu ZX
The nonlinear PCA learning rule in independent
32 Oja E 1997 154 7.33
component analysis
Weighted extreme learning machine for Zong WW; Huang GB;
33 2013 147 29.40
imbalance learning Chen YQ
A case study on using neural networks to perform
34 Yao JT; Tan CL 2000 143 7.94
technical forecasting of forex
Hopfield neural networks for optimization: study of Joya G; Atencia MA;
35 2002 142 8.88
the different dynamics Sandoval F
Li MB; Huang GB;
36 Fully complex extreme learning machine Saratchandran P; 2005 140 10.77
Sundararajan N
Ensemble of online sequential extreme
37 Lan Y; Soh YC; Huang GB 2009 139 15.44
learning machine
Multimodality medical image fusion based on
38 multiscale geometric analysis of Yang L; Guo BL; Ni W 2008 133 13.30
contourlet transform
A comprehensive review of current local features for
39 Li J; Allinson NM 2008 127 12.70
computer vision
Sorjamaa A; Hao J; Reyhani N;
40 Methodology for long-term prediction of time series 2007 125 11.36
Ji YN; Lendasse A
Top Authorship, Country, and Institutions

The list of most productive and influential authors is shown in Table 3. The most productive
authors are ordered by the maximum number of TP while the most influential authors are accounted
by TC. The table also describes authors with total citations, citations per paper and h-index. Cao and
Yang both have 74 publications, however, Cao received more citations of 1574 which is higher than
Yang’s citation of 510. These two are followed by Wang (TP = 72) and Zhang (TP = 64). Li and Liu
published same number of papers with a count of 60.
Table 3. Most Productive and Influential Authors in NC (1992–2018).
Rank Name Country Affiliation TP TC CPP h-Index

1 Cao JD China Southeast University 74 1574 21.27 23
2 Yang J China Beijing Institute of Technology 74 510 6.89 11
3 Wang J China Tsinghua University 72 374 5.19 12
4 Zhang HG China Northeastern University 64 899 14.05 17
5 Li J China Xidian University 60 528 8.80 13
6 Liu Y China Northeastern University 60 495 8.25 14
7 Zhang J China Beijing Institute of Technology 58 429 7.40 10
8 Wang Y China Central South University 55 344 6.25 10
9 Zhang Y China Tongji University 54 448 8.30 11
10 Yuan Y China Chinese Academy of Sciences 52 615 11.83 15
11 Li XL China Chinese Academy of Sciences 50 461 9.22 12
12 Sanchez VD USA University of Miami 50 197 3.94 7
13 Wang D China Dalian University of Technology 49 565 11.53 13
14 Wang L China Wuhan University 48 662 13.79 12
15 Liu J China Qingdao Agricultural University 45 215 4.78 8
16 Huang TW Qutar Texas A&M University 44 496 11.27 13
17 Liu YR China Yangzhou University 43 712 16.56 14
18 Zhang H China PLA University of Science & Technology 43 365 8.49 11
19 Zhang L China Hong Kong Polytechnic University 43 323 7.51 12
20 Gao XB China Xidian University 42 362 8.62 12
Again, Cao tops the list of most influential authors with TC of 1574. Zhang HG, Liu YR, Wang L
and Yuan Y are next in the list with TC of 899, 712, 662, and 615, respectively. The maximum citations
per paper (CPP) were attained by Cao (21.27), Liu (16.56), Zhang (14.05), Wang (13.79), and Yuan (11.83).
The h-index is again highest for Cao (23). Zhang (17) and Yuan (15) comes second and third
highest in the list. They are followed by Liu YR and Liu Y with same h-index of 14. Figure 4 conveys
similar information as in Table 3, for example the circles representing Cao and Zhang are the biggest
followed by Wang and Huang. Further, it depicts the author co-citation network and thus describes
the disciplinary ties between them.
The researchers from various countries are publishing in one of the computer sciences leading
journal of neurocomputing. The list of leading 25 countries which are publishing in NC is shown
in Table 4. Apart from total papers, the table also mentions other indicators such as: total
citations, citations per paper, and h-index. The countries are ordered according to the total number
of publications.
The People’s Republic of China is the most productive country which lies on the first spot
with a total publication count of 5179. It is followed by the USA (1498), England (590), Spain (564),
and Germany (492). Surprisingly, there is no developing country in the list of top 10 most productive
countries. India Ranks 11th in the list, which is a developing nation with 277 publications. The ranking
of most influential countries remains the same with respect to the most productive countries for China
(TC = 45,688) and the USA (TC = 13,933). Interestingly, then comes Singapore with 8764 citations
in only 278 publications. It is then followed by England (6596), Germany (5145), and Spain (4880).
The citations per paper shows a different image of the influence of the countries. Singapore tops the
Again, Cao tops the list of most influential authors with TC of 1574. Zhang HG, Liu YR, Wang L
and Yuan Y are next in the list with TC of 899, 712, 662, and 615, respectively. The maximum citations
per paper (CPP) were attained by Cao (21.27), Liu (16.56), Zhang (14.05), Wang (13.79), and Yuan
(11.83).
The h-index is again highest for Cao (23). Zhang (17) and Yuan (15) comes second and third
highest in the list. They are followed by Liu YR and Liu Y with same h-index of 14. Figure 4 conveys
similar
list withinformation
the highest as in of
CPP Table 3, for
31.53. example
Then comes the circles(17.58),
Belgium representing
FinlandCao and Zhang
(16.34), areNetherlands
and The the biggest
followed
(12.7). by Wang
These and Huang.
three countries Further,
were it depicts
not even theof
in the list author
top 10co-citation networkcountries.
most productive and thus There
describes
is a
the disciplinary ties between them.
total of 12 countries whose CPP is more than 10.
Figure 4.
Figure 4. Author
Author Co-Citation
Co-Citation Analysis.
Analysis.
The researchers from various countries are publishing in one of the computer sciences leading
Table 4. Most Productive Countries publishing in NC (1992–2018).
journal of neurocomputing. The list of leading 25 countries which are publishing in NC is shown in
Table 4. Apart from total papers, the table also mentions other indicators such as: total citations,
Rank Country TP TC CPP h-Index
citations per paper, and h-index. The countries are ordered according to the total number of
Peoples R China 5179 45,688 8.82 63.00
publications. 1
2 USA 1498 13,933 9.30 46.00
3 England 590 6596 11.18 37.00
4 Table 4. Most
SpainProductive Countries
564 publishing
4880 in NC (1992–2018).
8.65 31.00
5 Germany 492 5145 10.46 30.00
Rank Country TP TC CPP h-Index
6 Japan 439 3584 8.16 27.00
7 1 Peoples
France R China 5179
346 45,688
3909 8.82 63.00
11.30 30.00
8 2 AustraliaUSA 1498
343 13,933
2846 9.30 46.00
8.30 25.00
9 3 ItalyEngland 590
294 6596282511.18 37.00
9.61 26.00
10 4 Singapore Spain 564
278 48808764 8.65 31.00
31.53 35.00
11 5 IndiaGermany 277
492 5145304610.46 11.00
30.00 26.00
12 6 South KoreaJapan 276
439 35843016 8.16 10.93
27.00 27.00
13 7 Brazil France 256
346 3909189911.30 7.42
30.00 21.00
14 8 Canada Australia 253
343 28462481 8.30 9.81
25.00 27.00
15 Taiwan 244 2516 10.31 25.00
9 Italy 294 2825 9.61 26.00
16 Iran 174 1511 8.68 20.00
10 Singapore 278 8764 31.53 35.00
17 Saudi Arabia 170 1550 9.12 21.00
18 11 FinlandIndia 277
149 3046243411.00 26.00
16.34 23.00
19 12 Poland South Korea 276
139 3016142710.93 10.27
27.00 23.00
20 Belgium 118 2074 17.58 21.00
21 The Netherlands 111 1410 12.70 20.00
22 Scotland 104 840 8.08 16.00
23 Mexico 101 686 6.79 15.00
24 Greece 86 900 10.47 17.00
25 Malaysia 77 393 5.10 10.00
ranking of most influential countries remains the same with respect to the most productive countries
for China (TC = 45,688) and the USA (TC = 13,933). Interestingly, then comes Singapore with 8764
citations in only 278 publications. It is then followed by England (6596), Germany (5145), and Spain
(4880). The citations per paper shows a different image of the influence of the countries. Singapore
tops the list
Publications 2018,with
6, 32 the highest CPP of 31.53. Then comes Belgium (17.58), Finland (16.34), and The
10 of 22
Netherlands (12.7). These three countries were not even in the list of top 10 most productive countries.
There is a total of 12 countries whose CPP is more than 10.
With
With respect
respect toto the
the h-index,
h-index, China
China tops
tops the
the list
list with
with a value of 63 followed by USA (46), England
(37), Singapore (35), and Spain (31). Then Then France
France and
and Germany
Germany share
share the
the same
same h-index
h-index value
value of
of 30.
30.
The dominance of China can also be seen in the the Figure
Figure 55 which
which describes
describes the
the co-citation
co-citation analysis of
countries. The inference from this visualization shows that, almost every time, a paper paper originating
originating
from China is cited along with papers originating from other countries.
cited along with papers originating from other countries.
Figure 5.
Figure 5. Countries
Countries Co-Citation
Co-Citation Analysis.
Analysis.
The institution-wise ordering is displayed in Table 5. This table shows the total publications,
The institution-wise ordering is displayed in Table 5. This table shows the total publications,
total citations, citations per paper and h-index of institutions. Table 5 presents the most productive
total citations, citations per paper and h-index of institutions. Table 5 presents the most productive
institutions which have contributed to NC publications. The Chinese Academy of Sciences, China,
institutions which have contributed to NC publications. The Chinese Academy of Sciences, China,
produced 526 total papers with total citations of 4752. The second spot is taken by Harbin Institute of
Technology, also from China, with 219 papers. Southeast University from China takes the third spot
with 206 occurrences. The total papers from the institute with total citations and citations per paper
(CPP) are also given in the table, along with the h-index of each institution. As can be seen, most of the
institutes in the list belong to China. Interestingly, most of the universities in this table are from China.
However in terms of TC, Nanyang technological university, China stands at the top with
6862 citations followed by Chinese Academy of Sciences (4752) and Southeast University (3267).
The institutes with the highest average citation per paper (CPP) were Nanyang Technological
University, Singapore (46.68), National University of Singapore (27.46), and Southeast University
(15.86). There are 11 institutions in this list of top 25 which have a CPP of at least 10.
Two institutes have an h-index of 31, Chinese Academy of Sciences and Southeast University,
both are from China. They are followed by the Nanyang Technological University (30), Harbin Institute
of Technology, China (23), and Northeastern University, China (23). The dominance of China is also
evident here as most of the institutions in Table 5 are from China. However, among the institutions,
as shown by the institution co-citation network in Figure 6, the dominance of the Chinese Academy
of Sciences can be concluded, which overlaps with almost all the other institutions. This determines
that almost every time the publications from Chinese Academy of Sciences are cited along with all
other institutions.
Figure 6. Institution Co-Citation Analysis.

Figure 6. Institution Co-Citation Analysis.
4. Bibliographic Landscape
Table 5. Most Productive and Influential Institutions in NC (1992–2018).
This section demonstrates the disciplinary links with the help of bibliographic coupling. The
VOSviewer visualization toolInstitute
Rank is used(Countries)
to show the coupling betweenTP TC
the authors, CPP
countries h-Index
and the
institutions.
1 Chinese Academy of Sciences, China 526 4752 9.03 31
2We have first shown Harbinthe
Institute of Technology, China 219 2123 9.69
bibliographic coupling between the authors in Figure 7. The authors 23
3 Southeast University China, China 206 3267 15.86 31
are connected by the link with different widths. More width shows more intersection or references of
4 Nanjing University of Science Technology, China 180 1943 10.79 22
these5 authors, or degree of
Huazhong overlapofbetween
University the reference
Science Technology, lists, and 169
China thus more
1662 coupling.
9.83 Moreover,
21
each6node representing the authorsUniversity,
Tsinghua is also marked
China with three colors,166 red, blue
1243and green.
7.49 Each19color
7
consisting of group ofShanghai
countries Jiao TongaUniversity,
forms China
cluster which represents that164 1508
these countries 9.20
in a cluster21have
cited8each other’s paper with Xidian
more University, China
frequency. In the prominent cluster 158 shown
1178in red7.46 19 J,
color, Wang
9 Zhejiang University, China 158 1167 7.39 18
Yang 10
J, Yuan Y are the authors whose papers are more cited by the other
Northeastern University, China 157
authors
1492
in 9.50
that cluster.
23
The
Other11 cluster is of a green color with authors such as: Zhang
University Of Electronic Science Technology of China, China J, Wang D,
149 Zhang
1395 HG, Zhang
9.36 Y, and
21 so
on. Hammer B, Chen I, Wang GR, and so on form the third cluster of a blue color. We have mentioned
12 Nanyang Technological University, Singapore 147 6862 46.68 30
the author’s name, with the last name followed by the initials of the first name as there are 17
13 Xi An Jiaotong University, China 136 1588 11.68 many
14 Beihang University, China 132 884 6.70 16
Chinese authors whose names match closely.
15 Centre National De La Recherche Scientifique CNRS, France 128 1704 13.31 22
Figure 8 shows Dalian
16 the bibliographic
University ofcoupling
Technology,of China
the top countries/territories
127 1104publishing
8.69 in the 18NC.
The 17
countries are denoted by the
University of circular
Californianode
System,with different colors.126
USA The countries
1276 are
10.13connected
16 by
the 18
link with differentKing Abdulaziz
widths. More University,
widthSaudi
showsArabia 120
the more intersection 1302 10.85
or references of 21these
19
countries, or the Hong
degree Kong Polytechnic
of overlap University,
between Hong Kong
the reference 114 more
lists, and thus 1350 11.84
coupling. 20
20 University of Chinese Academy Of Sciences CAS, China 106 729 6.88 16
21 South China University of Technology, China 99 624 6.30 13
22 Chongqing University, China 98 1194 12.18 19
23 National University of Singapore, Singapore 98 2691 27.46 20
24 Tianjin University, China 97 613 6.32 13
25 University of London, England 96 1005 10.47 20
4. Bibliographic Landscape
This section demonstrates the disciplinary links with the help of bibliographic coupling.
The VOSviewer visualization tool is used to show the coupling between the authors, countries and
the institutions.
We have first shown the bibliographic coupling between the authors in Figure 7. The authors are
connected by the link with different widths. More width shows more intersection or references of these
authors, or degree of overlap between the reference lists, and thus more coupling. Moreover, each node
representing the authors is also marked with three colors, red, blue and green. Each color consisting of
group of countries forms a cluster which represents that these countries in a cluster have cited each
other’s paper with more frequency. In the prominent cluster shown in red color, Wang J, Yang J, Yuan Y
are the authors whose papers are more cited by the other authors in that cluster. The Other cluster is
of a green color with authors such as: Zhang J, Wang D, Zhang HG, Zhang Y, and so on. Hammer B,
Chen I, Wang GR, and so on form the third cluster of a blue color. We have mentioned the author’s
name, with the last name followed by the initials of the first name as there are many Chinese authors
whosePublications
names match closely.
2018, 6, x FOR PEER REVIEW 12 of 21
Figure 7. Bibliographic coupling of the authors in NC.

Figure 7. Bibliographic coupling of the authors in NC.
Figure 8 shows the bibliographic coupling of the top countries/territories publishing in the NC.
The countries are denoted by the circular node with different colors. The countries are connected by
the link with different widths. More width shows the more intersection or references of these countries,
or the degree of overlap between the reference lists, and thus more coupling.
Two countries are said to be bibliographically coupled if there is intersection between the papers
cited by them. Among all the countries, China is shown as the prominent one in Figure 8 which also is
the center node of the cluster between the countries such as Singapore, South Korea, India, Turkey,
and Saudi Arabia. This suggest that these countries are most likely working on similar research areas
and also referencing similar work. Among them, most probably all of other countries in this cluster are
citing papers from China. The other visible clusters shown in red color are countries such as the USA,
England, Japan, Germany, and France. Spain, Brazil, Italy, Canada, and Taiwan form the third cluster
with a green color.
In the last visualization of this section, we have shown the bibliographic coupling among several
institutions as shown in Figure 9. The Chinese Academy of sciences is the prominent node (institution)
in the red cluster. Other institute in this clusters are Xidian University, National University of Singapore,
Figure 8. Bibliographic coupling of the countries publishing in NC.

Peking University, and so on. This strong bibliographic coupling for Chinese Academy of Sciences
shows that most of the publications of other institutions in this cluster have cited its paper twice or
more. The cluster with the blue color has universities such as South East University, Harbin institute
of technology, King Abdulaziz University, and so on. Nanyang technology of university, Northeastern
university, University of Granada, and
Figure 7. so on form
Bibliographic the group
coupling of institutes
of the authors in NC. in the third cluster.
is the center node of the cluster between the countries such as Singapore, South Korea, India, Turkey,
and Saudi Arabia. This suggest that these countries are most likely working on similar research areas
and also referencing similar work. Among them, most probably all of other countries in this cluster
are citing papers from China. The other visible clusters shown in red color are countries such as the
USA, England, Japan, Germany, and France. Spain, Brazil, Italy, Canada, and Taiwan form the third
cluster with a green color.
In the last visualization of this section, we have shown the bibliographic coupling among several
institutions as shown in Figure 9. The Chinese Academy of sciences is the prominent node
(institution) in the red cluster. Other institute in this clusters are Xidian University, National
University of Singapore, Peking University, and so on. This strong bibliographic coupling for Chinese
Academy of Sciences shows that most of the publications of other institutions in this cluster have
cited its paper twice or more. The cluster with the blue color has universities such as South East
University, Harbin institute of technology, King Abdulaziz University, and so on. Nanyang
technology of university,
FigureNortheastern university,
8. Bibliographic coupling ofUniversity ofpublishing
the countries Granada, in
and so on form the group
NC.
Figure 8. Bibliographic coupling of the countries publishing in NC.
of institutes in the third cluster.
Two countries are said to be bibliographically coupled if there is intersection between the papers
cited by them. Among all the countries, China is shown as the prominent one in Figure 8 which also
Figure 9. Bibliographic coupling of the institutions publishing in NC.

Figure 9. Bibliographic coupling of the institutions publishing in NC.
5. Document Co-Citation Network
This section uses citescape for visualization of NC publications. Citespace is an open source Java
based application software used for visualizing trends from metadata of scientific literature.
Furthermore, document co-citation network analysis is studied along with the visualization of
different document co-citation clusters and the references with strong citation bursts.
The document co-citation network helps to explore the citation base of NC publications and can
5. Document Co-Citation Network

This section uses citescape for visualization of NC publications. Citespace is an open source
Java based application software used for visualizing trends from metadata of scientific literature.
Furthermore, document co-citation network analysis is studied along with the visualization of different
document co-citation clusters and the references with strong citation bursts.
The document co-citation network helps to explore the citation base of NC publications and
can be seen in Figure 10. There are nodes and links in the given network. The nodes in Figure 10
represents the cited reference, the highly cited references are labeled with their first author and its year
of publication.
Publications 2018, 6,The size
x FOR of aREVIEW
PEER node is proportional to its number of citations count. 14 of 21
Figure 10. Document co-citation analysis.

Figure 10. Document co-citation analysis.
The top 10 most cited references by NC publications from various sources (Journals, conferences,
etc.) The top 10 most
are tabulated cited references
in Table 6. The firstby NCpaper
is the publications
by Huang from various
et al. sources
[49] which (Journals,
proposes a newconferences,
learning
etc.) are tabulated in Table 6. The first is the paper by Huang et al. [49] which
approach called the extreme learning machine (ELM) for regression and multiclass classification. proposes a new learning
The
approach called the extreme learning machine (ELM) for regression and
paper has been cited 1283 times according to WoS. The second paper by Huang et al. [42] discussesmulticlass classification.
The
the paper
theoryhasandbeen cited 1283oftimes
applications ELM.according to WoS.
Third ranked Thepaper
is the second
bypaper
ChangbyetHuang
al. [50]etwhich
al. [42] discusses
proposes a
the
library for support vector machine (SVM) called LIBSVM. The fourth paper is a survey on ELM bya
theory and applications of ELM. Third ranked is the paper by Chang et al. [50] which proposes
library
Huangfor support
et al. [51]. Itvector
is verymachine
interesting(SVM) called
to note thatLIBSVM.
out of theThetenfourth paper
tabulated is a survey
articles six are onby ELM
Huang,by
Huang et al. [51]. It is very interesting
out of which three are co-authored by Chen. to note that out of the ten tabulated articles six are by Huang,
out of which three are co-authored by Chen.
Table 6. Top 10 Highly Cited References in NC.
Rank Title Year Source Authors

Extreme Learning Machine for Regression IEEE transactions on systems, Huang GB, Zhou H, Ding
1 2012
and Multiclass Classification man, and cybernetics X, Zhang R
Extreme learning machine: Theory and Huang GB, Zhu QY, Siew
2 2006 Neurocomputing
applications CK
ACM Transactions on
LIBSVM: A library for support vector
3 2011 Intelligent Systems and Chang CC, Lin CJ
machines
Technology
International Journal of
Hung GB, Wang DH, Lan
4 Extreme learning machines: a survey 2011 Machine Learning and
Y
Cybernetics
Letters: Convex incremental extreme
5 2007 Neurocomputing Huang GB, Chen L
learning machine
Enhanced random search based
incremental extreme learning machine
Universal Approximation Using
IEEE TRANSACTIONS ON Huang GB, Chen L, Siew
Table 6. Top 10 Highly Cited References in NC.
Rank Title Year Source Authors

Extreme Learning Machine for Regression IEEE transactions on systems, Huang GB, Zhou H,
1 2012
and Multiclass Classification man, and cybernetics Ding X, Zhang R
Extreme learning machine: Theory Huang GB, Zhu QY,
2 2006 Neurocomputing
and applications Siew CK
LIBSVM: A library for support ACM Transactions on Intelligent
3 2011 Chang CC, Lin CJ
vector machines Systems and Technology
International Journal of Machine Hung GB, Wang DH,
4 Extreme learning machines: a survey 2011
Learning and Cybernetics Lan Y
Letters: Convex incremental extreme
learning machine
Enhanced random search based
incremental extreme learning machine
Universal Approximation Using
IEEE TRANSACTIONS ON Huang GB, Chen L,
7 Incremental Constructive Feedforward 2006
NEURAL NETWORKS Siew CK
Networks With Random Hidden Nodes
Graph Embedding and Extensions: IEEE Transactions on Pattern
Yan SC, Xu D, Zhang B,
8 A General Framework for 2007 Analysis and
Zhang HJ, Yang Q, Lin S
Dimensionality Reduction Machine Intelligence
IEEE Transactions on Pattern Felzenszwalb PF, Girshick
Object detection with discriminatively
9 2010 Analysis and RB, McAllester D,
trained part-based models
Machine Intelligence Ramanan D.
Miche Y, Sorjamaa A,
OP-ELM: Optimally Pruned Extreme IEEE Transactions on
10 2010 Bas P, Simula O, Jutten C,
Learning Machine Neural Networks
Lendasse A
5.1. Cluster Detection and Analysis

The research patterns and emerging trends of NC publications are explored using CiteSpace.
Figure 11 displays the document co-citation clusters of NC publications. The title term of each
cluster is extracted from the title of the articles cited by NC publications using three methods namely
log-likelihood test (LLR), mutual information test (MI), and term-frequency and inverse-document
frequency (TF-IDF). For the NC publications there are a total of 187 clusters out of which the top
10 are as in the Table 7 along with the top terms from each of the above-mentioned methods LLI, MI,
and TF-IDF. Thereby, if considering LLR labels, then all the members of cluster 0 have spiking neurons
as a common research theme and cluster 1 has neural networks in common. This can further be seen
graphically in Figure 11 where all the clusters are shown. A total of 91 citing documents form the
cluster ID 1 and are labelled neural networks by LLR. It is a fairly young cluster. With a total of 84 citing
documents, cluster ID 2 is formed and is labelled Theoretical Results by LLR. Cluster ID 3 is formed of
76 citing documents and is labelled as Face Recognition by LLR. Cluster naming in Figure 11 has been
done using LLR, which visualizes these clusters over the document co-citation analysis network.
From Figure 11 and Table 7 it is quite evident that the three largest clusters are spiking neurons,
neural networks, and face recognition. Neural networks is the oldest cluster and Class is the youngest
cluster. The minimum value of silhouettes is 0.889 which shows good clustering. The largest cluster 0 is
of size 97 and a silhouette of 0.919 and is labeled spiking neurons by LLR. Figure 12 shows the timeline
view of the document co-citations of top 24 largest clusters. All of these clusters are plotted in a
horizontal manner. Further, it depicts the sequence of features of every cluster, which includes citation
patterns and relationships among the other clusters. The temporal spread of all the cluster can be seen
in Figure 12. Spiking neuron was a top research interest from 1992 to 2005 whereas neural networks
was from 2002 to 2014. Moreover, a strong connection can be seen between the neural network cluster
and convolution neural networks which is also a very obvious relationship. The temporal span of
convolutional neural network as shown in Figure 12 is from 2008 and continues until the year 2017.
Figure 11. Document co-citations clusters.

Figure 11.Document
Figure11. co-citationsclusters.
Document co-citations clusters.
Figure 12. Timeline view of the document co-citations.

Table 7. Top 12 clusters in NC publications.
Cluster ID Size Silhouette Label (TFIDF) Label (LLR) Label (MI) Mean (Year)
0 89 0.919 Spiking neurons Spiking neurons Nonlinear interactions 1998
1 91 0.938 Neural networks Neural networks Nonlinear interactions 2007
2 84 0.889 Neural networks Theoretical results Nonlinear interactions 1990
3 76 0.916 Face recognition Face recognition Nonlinear interactions 2007
Independent Independent
4 74 0.944 Nonlinear interactions 1997
component analysis component analysis
5 59 0.948 Neural networks Conjugate Gradient Nonlinear interactions 1991
6 49 0.954 Neural networks Periodic solution Nonlinear interactions 2003
7 47 0.934 Neural networks Kernel method Nonlinear interactions 1999
Spatio-temporal
8 42 0.929 Visual cortex Nonlinear interactions 1995
receptive fields
9 40 0.891 Computational model Weakly electric fish Nonlinear interactions 1996
Extreme learning Extreme learning
10 37 0.982 Nonlinear interactions 2008
machine machine
11 36 0.977 Class Fuzzy systems Nonlinear interactions 2013
Publications
5.2. References with Strong2018, 6, x FOR PEER
Citation REVIEW
Bursts 17 of 21
Publications
5.2. 2018, 6,
References x FOR
with PEER
Strong REVIEW Bursts
Citation 17 of 21
Publications
5.2. 2018, with
References 6, x FOR PEERCitation
Strong REVIEW Bursts 17 of 21
Publications 2018, 6,
5.2. References x FOR
with PEERCitation
Strong REVIEW Bursts 17 of 21
ResearchPublications 2018, 6, x FOR PEER REVIEW 17 of 21
5.2.articles
References
Publications
Research
Publications getting
2018,
2018, with
6, x a boom
Strong
x FOR
articles
6, FOR PEER
PEER of citations
Citation
REVIEW
getting a
REVIEW boom in citations
Burstsof a period inof atime can of
period give an can
time insight
giveofantheinsight
emerging
17 of
of of
17 21
ofthe
21
5.2. References
Research
Publications with Strong
2018, 6,articles
x FOR PEER Citation
getting a
REVIEW Bursts
boom of citations in a period of time can give an insight of
17 the21
developments 5.2. References
inResearch
the
Publications
5.2. with
research
2018,
References 6, x
with Strong
articles
domain.
FOR PEER
Strong Citation
getting a Bursts
boom
Citation
REVIEW
Citation of
burstscitations
depict
Burstsof domain. in
thea period
articles of
to time
which can
thegive an
research insight of
fraternity
17 ofthe
21
emerging
Research
Publications
5.2. developments
2018,
References
emerging articles
6, x
with FOR PEER
Strong
developments in the
getting a
REVIEW
Citation
in research
boom
Bursts
thea research citations
domain. Citation
in a
Citation bursts
period of
bursts depict
time the
can articles
give an to which
insight of
17 the
ofthe
21
5.2. Research
References
Publications
emerging
5.2. 2018,
References
pays most attention. articles
with
6,
developments
The with
top getting
Strong
x FOR PEER
Strong
30 Citation
inREVIEW boom
with of
Bursts
theattention.
Citation
references research
Bursts citations
domain.
the highest incitation
a period
Citation of depict
bursts
burststime
depict
are
thegive
can articles
thegive
shown articles
in
to which
anTable
insight of ofthe
8. 17
to which the
21
the
research
5.2. fraternity
Research
References
Publications
emerging 2018, with
6, x pays
articles
Strong
FOR
developments PEERmost
getting a
Citation
REVIEW
in the boom
Bursts
researchofThe top
domain. 30
citations inreferences
a
Citationperiod with
of
bursts the
time
depict highest
can
the citation
an
articles
research fraternity pays most attention. The top 30 references with the highest citation bursts are
Research articles getting to bursts
insight of
17
which ofare
the
21
the
5.2. References
emerging
research with Strong
developments theaaattention.
Citation
in boom
Burstsof
research citations Citation
domain. in a period of depict
bursts time can thegive an insight
articles of the
to which the
shown
emerging
research
shown
emerging infraternity
Research
Research
in Table
5.2. References
fraternity
ResearchTable 8.
developments
pays
articles
8. Strong
with
developments
articles
pays
articles
most
getting
Citation
in
getting
most
getting
in the
boom
Burstsof
theaaattention.
research
boom
boom
researchof
of
The
The
top 30Citation
citations
domain.
citations
top
citations
domain. 30
in
in
in
references
aa period
references
a
Citation period
with
of
bursts
period of
with
of
bursts
the can
time
depict
time
the
time
depict
highest
thegive
can
can
thegive
highest
give
citation
an
articles
an
an
articles
bursts
insight
insight
citation
insight
to
of
to which
which
of
bursts
of
are
the
the
are
the
5.2.
shown References
Research
research
emerging in Table with
fraternity8. Strong
articles
developmentspays Citation
getting
most
in the a Bursts
boom
attention.
researchof citations
The top
domain. 30 in a period
references
Citation of
with
bursts time
the
depict can give
highest
the an insight
citation
articles to of
bursts
which the
are
the
5.2. References
Research
research
emerging
shown
emerging in with
Table
fraternity 8.Strong
articles
developments
Table 8.
developments Top
pays Citation
30
most
in
in References
gettingthe
the Burstswith
a research
boom
attention.
researchofThe the
domain.
domain. Strongest
citations
The top 30Citation Citation
inreferences
a period
references
Citation ofBursts.
with
bursts
bursts time
the can
depict
depict give
highest
the
the an insight
citation
articles
articles to
to of are
bursts
which
which the
are
the
research
emerging fraternity
Research developmentspays
articles most
getting
in 8.theattention.
a boom
research of top
citations
domain. 30 in a period with
of the
time highest
can give citation
an bursts
insight of the
shown
research
emerging
shown
research
infraternity
ResearchTable 8. pays
articles
developments
infraternity
Table 8. pays most
getting
Table
most attention.
aattention.
Top
in 8.the boom ofThe
30 References
research top
citations
domain.
The with
top 30Citation
inreferences
the
Citation
bursts
aStrongest
period of depict
with
bursts the
time
Citation
depict
thegive
highest
can
Bursts. articles
thegive
to which
citation bursts
an insight
articles
the
are
of the
to which
research
shown
emerging in fraternity
ResearchTable 8. pays
articles
developments most
Table
getting
in the attention.
Top
a boom
researchofThe
30 References with30
top
citations
domain. 30the
inreferences
references
Strongest
a
Citation period with
with
of
bursts
the
the
Citation
time
depict
highest
highest
Bursts.
can
the
citation
citation
an
articles
bursts
bursts
insight
to of
which
are
are
the
research
shown
emerging in
References
fraternity
Table 8.
developmentspays most
Table
in 8.
the attention.
Top research
Year
The
30 References top
domain.
Strength with30Citation
the
Begin
references
Strongest
End
with theBursts.
Citation
bursts depict highest
the citation
articles
1992–2018
bursts the
to which are
research
shown
shown
emerging infraternity
in Table
Table 8. pays
8.
References
developments most
Table 8.
in 8.theattention.
Top The
30 References
Year
research top
with
Strength
domain. 30thereferences
Begin Strongest
End with theBursts.
Citation highest citation
1992–2018 bursts are
research
shown in fraternity
Table 8. pays
References most
Table attention.
Top Year The
30 References with30Citation
top
Strength the references
Begin bursts
Strongest
End withdepict
the
Citation the1992–2018
highest
Bursts. articles to which
citation bursts the
are
research
shown fraternity8. pays most
Table attention.
8. Top
Top Year The
30 References
References top
with30the
thereferences
Strongest with
End CitationtheBursts.
highest
Bursts.
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂ citation bursts are
J, in TableReferences Strength Begin 1992–2018
Hertz J, 1991,research
Hertz Theory
shown
Intro in fraternity
1991, Intro
Table Theory
8.
References
Neural, V, Table
pays most
Neural,
P 8.
V, P1991 30
attention.
1991
Year The with
top
15.3824
Strength
15.3824 30
1994 1994
BeginStrongest
references
1999
End
1999 Citation
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
with the highest citation
1992–2018 bursts are
Hertz J, in
shown 1991, Intro
Table Theory
References
8. Table
Neural, 8.
V, PTop 30 References
1991 Strength
Year with
15.3824 the
1994
BeginStrongest
1999 ▂▂▂▂▂▂▂▂
End Citation Bursts.
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
1992–2018
Hertz J, 1991, Intro Theory
References Table
Neural, 8.
8. PTop
Table V, Top 3030 References
References
1991 Strength
Year with
with the
15.3824 the
1994
Begin Strongest
End Citation
Strongest
1999 ▂▂▂▂▂▂▂▂
Citation Bursts.
Bursts. 1992–2018
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
shown
Hertz J, in Table
1991, Intro 8.
Theory
References Table V,
Neural, 8. PTop 30 References
1991 Strength
Year with the
15.3824 Strongest
1994
Begin End ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
1999 Citation Bursts. 1992–2018
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
HornikJ, K,
Hertz 1989,
1991, Neural
Intro Networks,
Theory
ReferencesNeural, V2,
TableV2,
V, P359 30 References
8. PTop 1989 Strength
1991
Year 12.3758
with the
15.3824 1994
1994
Begin 1997
Strongest ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
End Citation
1999 Bursts. 1992–2018
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Hornik
Hornik K, 1989,
Hertz J,K,
Neural 1989,
1991, Neural
Networks,
Intro Networks,
V2,Neural,
References
Theory
References Table 8.PPP359
P359 V2,
V, Top 1989
1991
Year 12.3758
198930 References
12.3758
Year Strength 1994
with
15.3824
Strength 1994
Begin
the
1994
Begin 1997
1997
End
Strongest ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
End Citation
1999 Bursts.1992–2018
1992–2018
Hornik
Hertz J, K, 1989,
1991, Neural
Intro Networks,
Theory Neural, V, P359 1989
1991 12.3758
15.3824 1994
1994 1997
1999 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Haykin
Hornik
Hertz J, S, 1994,
K, 1989,
1991,
References
Neural
Neural
Intro
Table
Networks
Networks,
Theory Neural,
8.
Comp,
V2,
V, P
TopV,
P359 30 References
Year
1989
1991
with
Strength
12.3758
15.3824
the Strongest
Begin
1994
1994
End
1997
1999
Citation
▂▂▂▂▂▂▂▂Bursts. 1992–2018
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Haykin S, 1994, References
Neural Table
Networks 8.
Comp, TopV, 30 References
Year
1994 with
Strength
10.6235 the Strongest
Begin
1996 2002 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
End Citation
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂Bursts. 1992–2018
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
Hornik
Hertz
Hertz
P
Haykin
J, K,
J, S, 1989,
1991,
1991, Neural
Intro
Intro
1994,
Networks,
Theory
Theory
References
Neural
Neural, V2,
V, PP359
Neural, V, P V,
Networks
1989
1991
1991 12.3758
15.3824
15.3824
Year Strength
1994 10.6235 1994
1994
Begin
1996 1997
1999
1999 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
End ▂▂▂▂▂▂▂▂
2002 1992–2018
Haykin S, 1994,
P Neural
Hornik
Hertz K,
J, K,
1991,Networks
1989, Neural
Intro Theory
ReferencesNeural,Comp,
Comp,
Networks, V2, P359
V, PP359 1989
1991
Year
1994 12.3758
15.3824
Strength
10.62351996 1994
Begin 1997
1999
End
1996 2002
2002
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂ 1992–2018
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
Haykin
Hornik
Hertz S, 1989,
J, K, 1994,
1991, Neural
Intro Networks
Networks,
Theory Neural,Comp,
V2, 1994
V, PP359V, 10.6235
1989
1991 12.3758
15.3824 1994
1994 1997
1999 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V, P P
Cybenko
Haykin
Hornik S,G, 1989,
1994,
1989, Mathematics
Neural
References
Neural OfComp,
Networks
Networks, Control,
V2, V, 1994
Year
1989 10.6235
Strength
12.3758 1996
Begin
1994 2002
1997 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
End ▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
1992–2018
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Hertz
P J,
Cybenko
Hornik 1991,
Haykin
Hornik Intro
K,G,1989,
S,G,
K, Theory
1989,Neural
1994,
1989, Neural,
Mathematics
Neural V,
Networks
Networks, P
Of Control,
Networks, V2, P359
Comp,
V2, V,
P3591991
1989
1994 15.3824
8.6326
12.3758
10.6235 1989 1994
1994
1996 1999
2002
12.3758 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
1997 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
1994 1997 ▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Hertz
P
Haykin
HornikJ, K,
1991,
And Systems
Cybenko S, Intro
1989,
1994,
1989, Theory Neural,
Mathematics
Neural
Neural V, PP359
OfComp,
Networks
Networks, Control,
V2, V, 1989
1991
1994
1989 8.6326
15.3824
10.6235
12.3758 1996
1994
1996
1994 1997
1999
2002
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
And Systems
Hertz J,K,
Cybenko
Haykin 1991,
S, G, Intro
1989,
1994, Theory Neural,
Mathematics
Neural V, PP359
OfComp,
Control, 1989
1994
1991 8.6326
10.6235
15.3824 1996
1994 1997
2002
1999 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Cybenko G, 1989,
P
And
P Mathematics
Hornik
Systems
Haykin
Rumelhart
Cybenko S, 1989,
1994,
De, OfNetworks
Neural
Neural
1986, Control,
Networks,
Networks
Parallel V2,
Of Comp,
Distributed,
V,
V, 1989
1989 12.3758
8.6326 1994
1996 1997
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Haykin
Hornik S,G,
K, 1989,
1994,
1989, Mathematics
Neural
Neural Networks
Networks, Control,
Comp, 1989
V,
V2, P359 1994
1989 10.6235
8.6326
12.3758 1996
19961996
1994 2002
1997
1997 ▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
And Systems Rumelhart
P
P
And
V1,
And
Systems
Haykin
Cybenko
Hornik
P318
RumelhartS,
K,
Systems
Cybenko
De,
1994,
G,
1989,
De,
1986, Parallel
Neural
1989,
Neural
1986,
Distributed,
Networks
Mathematics OfComp,
Networks,
Parallel V2, V,
Control,
P359
Distributed,
G, 1989, Mathematics Of Control,
1994
1986
1989
1994
1989
1986
1989
1994
10.6235
7.5576
8.6326
10.6235
12.3758
7.5576
8.6326
10.6235
1993
1994
1993
1996
2002
1994
1997
2002
1997
1994
1997
2002
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P Haykin
V1, P318
Hornik S, 1994,
K, 1989, Neural
Neural Networks
Networks, Comp, V,
V2, P359 1986
1989 7.5576
12.3758 1993
1994 1994
1997 ▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
Cybenko
And
P S,G,
Systems
Haykin De,
1994,1986,
1989, Parallel
Mathematics
Neural Distributed,
Networks Of Comp,
Control,
V, 1989
1994 8.6326
10.6235 1996
1996 1997
2002 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
PV1,
And P318
Cybenko
1986,
Cybenko G,
Systems
Rumelhart De,Rumelhart 1989,
De,
Parallel
G, 1989, Mathematics
1986, Parallel
Distributed,
Mathematics Of
Of Control,
Distributed,
Control, 1986
1989 7.5576
8.6326 1993
1996 1994
1997 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Haykin
Poggio
V1,
And P318S,
T, 1994,
1990,
Systems Neural
P IEEE, NetworksOfComp,
V78, P1481 V, 1994
1990
1989
1986 10.6235 1996
7.4954 19931993
8.6326
7.5576 1995
1996 2002
1998
1997
1994 ▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Rumelhart
Cybenko
P P318
Poggio
Haykin S,G,
T, De,
1990,
1994,1986,
1989, Parallel
Mathematics
PNeural
IEEE, V78, Distributed,
P1481
Networks Control,
1986 1989
7.5576
1994
1990 8.6326
10.6235
7.4954 1996
1996
1995 1997
1994
2002
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▃▃▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V1, P318 PAnd
V1,
And Systems
Rumelhart
Systems
Cybenko
Poggio T, G, De, 1986,
1989,
1990, P
Parallel
Mathematics
IEEE, V78, Of Comp,
Distributed,
P1481
V,
Control, 1989
1986
1990
1994 8.6326
7.5576
7.4954
10.6235 1996
1993
1995
1996 1997
1994
1998
2002
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
And Systems
V1, P318 De,
Cybenko 1986,
G, Parallel
1989, Distributed,
Mathematics Of Control, 1986
1989 7.5576
8.6326 1993
1996 1994
1997 ▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Chen
P
V1, S, T,
Rumelhart
Poggio
P318
Rumelhart
And 1991,
Systems De,
De,IEEE
1990, 1986,
1986,T Parallel
Neural
P IEEE,
Parallel Networ, V2,
Distributed,
V78, Networ,
P1481
Distributed, 1990
1986
1989 7.4954
7.5576
8.6326 1995
1993 1998
1994
1997 ▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Cybenko
Chen
Poggio
V1, S,T, G,
1991, 1989,
IEEE
1990, Mathematics
T Parallel
P IEEE,Neural Of Control,
V78, P1481 V2, 1991
1986
1990 7.2449
7.5576
7.4954 1996
1993
1995 1999
1994
1998 ▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P302
Chen AndP318
Rumelhart
Cybenko
V1, Systems
S,T,
P318 1991,
G, De,
IEEE
1989, 1986,
T Parallel
Neural
Mathematics Distributed,
Networ, V2,
Of Control, 1986
1989
1991 7.5576
8.6326
7.2449 1993
1996 1994
1997
1999 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Poggio
V1,
Poggio T, 1990,P302P318
P P318
IEEE, 1990,
V78, P IEEE, V78, P1481 1990
1986 7.4954
7.5576 1995
1993 1998
1994 ▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Rumelhart
And
Chen
Poggio
V1, Systems De,
S,T,1991,
1990,
Rumelhart P P1481
1986,
IEEE T Neural
IEEE,
De, Neural
1986,
1990
Distributed,
Networ, V2,
V78, P1481
Parallel Distributed,
7.4954
1991
1989
1990
1986 7.2449
8.6326
7.4954
7.5576
19951996
1995
1993
1998
1999
1997
1998
1994
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P302
Moody
And
Chen J,1991,
1989,
Systems
S,T, Computation, V1, 1991 7.2449 1996 1999 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Poggio
V1, P318
Rumelhart
Moody
Poggio
P302
Chen S,T, De,IEEE
1990,
J,1991,
1989,
1990,1986,T Parallel
Neural
P
Neural
P IEEE,
P IEEE,
IEEE
Networ,
V78, P1481
Computation,
V78,
V78, P1481
T Neural Networ,
V2,
Distributed,
V1,
V2,
1990
1986
1989
1990
1991
7.4954
7.5576
7.2193
7.4954
7.2449
1995
1993
1995
1996
1998
1994
1997
1998
1999 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P281
Moody Poggio
V1, P318
Rumelhart
P302
Chen S, T,
J,1991,
1989, 1990,
Neural
De,IEEE
1986, IEEE,
Computation,
T Parallel
Neural P1481
V1,
Distributed,
Networ, V2, 1990
1986
1989 7.4954
7.5576
7.2193 1995
1993
1995 1998
1994
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Poggio
Chen S, 1991, IEEE
V1,
P281 TT,
P318 1990,
Neural P IEEE, V78, P1481
Networ, 1991
1990
1989 7.2449
7.4954
7.2193 1996
1995
1995 1999
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Moody
Chen
P302
PoggioS, J,
T, 1989,
1991, Neural
IEEE
1990, Computation,
T Neural
P IEEE, V1,
Networ, V2,
V78, P1481 1991 1986
1991
7.2449
1990 7.5576 19961996
7.2449
7.4954 1993
1995 1994
1999
1999
1998 ▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P281
Chen
V1,
P302
Chen S,
P318
Moody S, 1991,
J, 1989,
1991, IEEE
IEEE T
Neural
T Neural Networ,
Computation,
Neural Networ, V2,
V1,
V2, 1989
1991 7.2193
7.2449 1995
1996 1997
1999 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V2, P302 Poggio
Pao
P281Y-H,
P302
Moody
Chen T, 1990,
1989,
S, J,1991, P
1989,IEEE IEEE,
Adaptive
Neural V78, P1481
Pattern
Computation,
T Neural Rec, V1,
Networ, V, P
V2, 1990
1991
1989
1991
7.4954
7.1573
7.2449
7.2193
7.2449
1995
1994
1996
1995
1996
1998
1999
1997
1999 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Poggio
Pao
P302
P281
Moody
Chen S,T,
P302Y-H, 1990,
1989,
J,1991,
1989, P IEEE,
Adaptive
Neural
IEEE V78, P1481
Pattern Rec, V1,
Computation,
T Neural Networ, V,
V2,P 1990
1989
1991
1989 7.4954
7.1573
7.2449
7.2193 1995
1994
1996
1995 1998
1997
1999
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Pao Y-H,
Poggio T, 1989,
1990, Adaptive
P IEEE, Pattern
V78, Rec, V1,
P1481 V, P 1990
1989 7.1573
7.4954
7.2193 1994
1995
1995 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Moody J, 1989,Moody
P302
P281
Chen
Moody
Pao
P281
Moody
P302
S,J,
Neural
Y-H,J,
1989,
1989,
J,1991,
1989,
Neural
Computation,
1991, IEEE
Neural
Neural
Computation,
T Neural Networ,
Computation,
Adaptive Pattern V2,
Rec,V1,
Computation, V, P
V1,
1991
1989
1989
7.2449
7.1573
7.2193
1996
1994
1995
1999
1997
1997 ▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Chen
Pao
P281 S, J,
Kohonen
Y-H, 1989,IEEE
T, 1990, PTIEEE,
Neural
Adaptive Networ,
V78,
PatternP1464 V,1989
V2,
Rec, V1,P 1991
1990
1989 7.2449 19951994
7.21936.3202
6.3202
7.2193
7.1573 1996
1995 1999
1997
1998
1997 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
V1, P281 Moody
P302
Kohonen
ChenY-H, T,
S,J,1991, Neural
1990, P Computation,
IEEE, V78, P1464 1989
1990
1991 7.2193
7.2449 1995
1996 1997
1998
1999 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P281
Pao
P281
Moody
P302
Kohonen 1989,IEEE T Neural
Adaptive
Neural
T, 1990,
Networ,
Pattern
Computation, V2,P
Rec, V1,
V,
P IEEE,Pattern
V78, P1464 1989
1990 7.1573
7.2193
6.3202 1994
1995
1996 1997
1998 ▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Pao
P281
MoodyY-H,J,S1989,1989, Adaptive
Neural Computation, Rec, V,
V1,P 1991
1989
1989 7.2449
7.1573
7.2193 1994
1995 1999
1997
1997 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Fahlman
P302
Kohonen
Pao Y-H, T,E,1990,
1990, Adv
PAdv
IEEE, Neural Informati,
V78, P1464 1990 6.3202 1996 1998 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P281
Fahlman
Moody
Kohonen J, S1989,
T,E,1990,
1989, Adaptive
1990,
Neural
P IEEE,
Pattern
Neural
Computation,
V78,
Rec, V1,
V,
Informati, P 1989
1989 7.1573
7.2193 1994
1995 1997
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Pao
Pao
Pao Y-H, 1989,Pao
V2,
Y-H,
Y-H,
Adaptive
P281P524
Fahlman
Moody
Kohonen
Y-H, J, 1989,
S1989,
T, E,1990,
1989,
Adaptive
Adaptive
Pattern
1990,
Neural
P Adv
IEEE,
Adaptive Rec, V, P1464
Pattern
Pattern
Neural
Computation,
V78,
Rec,
P1464
Pattern Rec,
V,
V, P
Rec, V1,
PInformati, P
V,1989
P
1990
1989
1989
1989
1990
1989
6.3202
7.1573
7.2193
6.3202
7.1573
1996
1994
7.1573 19941996
7.15736.3202
1990 1994
1995
1996
1994
1998
1997
1997
1997
1998
1997
1998
1997
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V2,
P281 P524 S
Fahlman
Kohonen T, E, 1990,
1990, P Adv
IEEE, Neural
V78, Informati,
P1464 1990
1989 6.3202
7.2193 1996
1995 1998
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Pao
V2, Y-H,
P524
Narendra
Fahlman
P281
Kohonen S 1989,
KE, S, Adaptive
1990,
1990, Ieee
Adv Pattern
Trans
Neural Rec,
Neural V,
Informati, P 1989
1990 7.1573
6.3202 1994
1996 1997
1998 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Y-H, ST,
Pao P524
Narendra
Kohonen
V2,
Fahlman
Kohonen KE,1990,
1989,
T,
T, 1990,
1990,
P IEEE,
Adaptive
S,1990,
1990,P IEEE,
P Adv
IEEE,
V78, P1464
Pattern
IeeeNeural
Trans
V78, Rec, V, P
Neural
V78, P1464
Informati,
P1464
1990
1989
1990
1990
6.3202
7.1573
6.2445
6.3202
6.3202
1996
1994
1995
1996
1996
1998
1997
1998
1998
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Kohonen T, 1990,
Pao
Netw,P V1,
Y-H,
Narendra
V2, P524
Fahlman
Kohonen IEEE,
V1,S1989,
K
T,P4 V78,
Adaptive
S,1990,
E,1990,1990, P1464
PAdv Pattern
IeeeNeural
IEEE, Trans Rec, V,1990
Neural
Informati,
V78, P1464 P 1990
6.32026.2445
1989
1990 7.1573
6.3202 19961995
1994
1996 1998
1998
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Netw,
Pao Y-H, ST,
Narendra
Fahlman
V2, P524 P4
1989,
KE,1990, Adaptive
S,1990,
1990, Pattern
IeeeNeural
Adv Trans Rec, V, P
Neural
Informati, 1990
1989 6.2445
6.3202
7.1573 1995
1996
1994 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Kohonen
Netw,
Fahlman
Funahashi
V2, P524
Narendra V1, S KP4
E,
K, S,1990,
1989,
1990,P IEEE,
Adv
Neural
Ieee V78,
Neural
Trans P1464
Informati,
Networks,
Neural V2, 1990
1990
1990 6.3202
6.2445
6.3202 1996
1995
1996 1998
1998
1998 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Fahlman
Kohonen
Funahashi S
V1,ST, E,
K, 1990,
1990,
1989, Adv
PNeural
IEEE, Neural
V78, Informati,
P1464
Networks, V2, 1990
1989 6.3202
6.3202
5.8544 1996
1996
1994 1998
1997 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Netw,
V2, P524
Fahlman
Narendra
Fahlman S E, 1990,
Kohonen Adv KP4
E,1990,
S,1990,
1990,
Neural P Adv
Ieee Neural
Trans
Informati, Informati,
Neural 1990 6.2445
6.3202 1995
1996 1998 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V2,
P183P524
Funahashi
Netw,
Narendra
V2, P524
Fahlman V1,ST, K,
P4
K E, 1989,
S,1990,
1990, IEEE,
Neural
Ieee V78, P1464
Networks,
Trans Neural V2, 1990
1989
1990 6.3202
5.8544
6.3202
6.2445 1996
1994
1996
1995 1998
1997
1998 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P183
Kohonen
Funahashi
Narendra
Netw,
V2, P524
Fahlman V1, T,
SK K,
P4
E,1990,
1989,
S,1990,
1990, PAdv
IEEE,
Neural
Adv
Neural
V78, Informati,
P1464
Networks,
Ieee Neural
Trans Neural 1990
V2,
Informati,
6.3202
1989
1990
1990
1990 5.8544
6.3202
6.2445
6.3202 19961994
1996
1995
1996 1998
1997
1998
1998
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
V2, P524 P183
Narendra
Rumelhart
Netw,
Funahashi
Narendra
V2, P524 V1,SK KP4
K, S,
De,
S, 1990,
1986,
1989,
1990, Ieee
Neural
Ieee Trans
Parallel Neural
Distributed,
Networks,
1990
1990 5.8544
6.2445
6.3202 1994
1995
1996 1997
1998
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Fahlman
Rumelhart
P183
Netw, V1, K E,
De,
P4 1990, Adv
1986,Neural Neural
Parallel Informati,
Distributed, 1990
1986
1989 6.2445
5.4868
5.8544 1995
1992
1994 1998
1994
1997 ▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Funahashi
Narendra
V2, P524
Fahlman
Netw,
V1,
P183 P V1,
Rumelhart
Funahashi SKK, S, 1989,
1990,
E,S,1989,
P4
De,
K, 1990, Ieee
Adv
1986,Neural Networks,
Trans
Neural
Parallel Neural V2,
Informati,
Distributed,
Networks, V2,
1990
1990
1986 6.2445
6.3202
5.4868 1995
1996
1992 1998
1998
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Netw,
Narendra
V2,
Narendra K S,V1, P524
1990,
P V1,
Ieee P4 1990,
Trans Ieee
NeuralTrans Neural 1989
1990
1990
1986 5.8544
6.2445
6.3202
5.4868 1994
1995
1996
1992 1997
1998
1998
1994 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
Funahashi
Netw,
P183
Narendra V1, De,
K,
P4
K S, 1986,
1989,
1990, Parallel
Neural
Ieee Distributed,
Networks,
1990 5.8544
6.2445 1994
1995 1997
1998 ▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V2,
V1,
P183PP524
Funahashi
Kohonen
Rumelhart
Funahashi
Netw,
Narendra V1, KK,
Teuvo,
De,
K,
P4 S, 1989,
1986,
1989,
1990, Neural
1989, Self
Parallel
Neural
Ieee Networks,
Org
Trans Ass V2,
Distributed,
Networks,
Neural
1990
V2, 6.24455.8544
1986
1989
1990 6.2445 19951992
5.4868 1992
1994
1995 1998
1994
1997
1998 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Netw, V1, P4 Kohonen
V1,
P183 P V1, P4
Funahashi Teuvo,
K, 1989,1989, Self
Neural Org Ass
Networks, 1989
1986 5.8544
5.3089
5.4868 1994
1996 1997
1994 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
Netw,
Narendra
P183
Memory,
Kohonen
V1,
P183P V1,Teuvo,
Rumelhart
Funahashi K
V, De,
K, P
De,
1986,
S,1989,
1990,
1989,
1986,
Parallel
Ieee
Neural Trans
Self
ParallelOrg Ass V2,
Distributed,
Neural
Distributed,
Networks, V2,
1989
1990
1989
1989
1986
5.8544
6.2445
5.3089
5.8544
5.4868
1994
1995
1996
1994
1992
1997
1998
1997
1997
1994 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Netw,
Memory,
P V1,V, P4 ▂▂▂▂▂▂▂▂
Kohonen
Rumelhart
V1,
P183
Funahashi
Funahashi K, 1989,
V1, P Neural
Netw,
Memory,
Rumelhart
Waibel
Kohonen V, K,P
Teuvo,
De,
P4
A,Teuvo,De,
1989,
1986,
P 1989,
1989,
1986,
Ieee Neural
Networks,
1989,
Self Networks,
Parallel
Parallel
T Acoust
Org Ass V2,
Distributed,
Distributed,
Speech,
Self Networks,
Org Ass V2, V37,
1990
1989
1986
1989
1989
6.2445
5.3089
5.4868
5.8544
5.3089
1995
1996
1992
1994
1996
1998
1997
1994
1997
1997
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Rumelhart
P183
Funahashi De,
K, 1986, Parallel Distributed, 1986
1989 5.4868 1992
5.8544 19941996
1994 1994
1997 ▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Waibel
P A,Teuvo,
Memory,
V1,
Kohonen
Rumelhart
P183 1989,
V,De,P1989,
Ieee Neural
1989,
1986, TParallel
Acoust
Self OrgSpeech,
Ass V2,
Distributed, 1989
V37, 5.85445.2033
1986
1989
1986 5.4868
5.2033
5.3089
5.4868
5.8544 1992
1994
1992 1997
1994
1997
1994 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V2, P183 Funahashi
V1,
P328P
Waibel
Memory,
Kohonen
V1, P
Rumelhart A, V, K,
1989,
P
Teuvo,
De, 1989,
Ieee Neural
1989,
1986, T Acoust
Self
ParallelNetworks,
Org Speech,
Ass
Distributed, V37, 1989
1986
1989 5.4868
5.3089 1994
1992
1996 1997
1994
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P183
P328
Waibel
Kohonen
V1, P
Memory, A,Teuvo,
V,1989,
P Ieee
1989, T Acoust
Self Org Speech,
Ass V37, 1989 5.8544
5.2033
5.3089 1994
1996 1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Rumelhart
P183
P328P A,V,
Kohonen
Memory, De,
Teuvo, 1986,
P 1986, 1989, Parallel
Self Distributed,
Org Ass 1986
1989 5.4868
5.2033 1992
1994 1994
1997 ▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Waibel
Kohonen
V1,
Rumelhart 1989,
Teuvo,
De, Ieee
1989,T Acoust
Self
ParallelOrgSpeech,
AssV1,V37,
Distributed, 1989
1986 5.3089
5.4868 1996
1992 1997
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Jacobs
Rumelhart De,Jacobs
1986,
P328
Memory,
Kohonen
Waibel
V1, P Ra,Ra,
A, V,1988,
Parallel Neural
P Neural
Teuvo,
1989, 1989,
Ieee Networks,
Distributed,
Self
T AcoustOrg AssV1,
Speech, P295
V37, 1988
1989
1986
4.6453
5.3089
5.2033
5.3089
5.4868 1996
1994
1996
1992
1996
1997
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
Memory,
P328
Waibel
Memory,
Kohonen V,
A,Teuvo,1988,
De,
P 1986,
P
1989,
V, Ieee
1989, Networks,
TParallel
Acoust
Self Distributed,
OrgSpeech, P295
AssV1,V37,1986 1988
5.48684.6453
1989 5.2033
5.3089 19921994
1994
1996 1996
1994
1997 ▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
V1, P V1, P Ra,
Jacobs
Waibel A, 1988,
1989, Neural
Ieee T Networks,
Acoust Speech, P295 1988
1986
1989 4.6453
5.4868
5.2033 1992
1994 1996
1994
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Memory,
P328
Kohonen
V1,
P328 P
Waibel
Jacobs A,
Ra,
V, P
Teuvo,
1989,
1988, 1989,
Ieee
Neural T Self
Acoust
Networks, AssV1,V37,
OrgSpeech, V37,
P295 1989
1988 5.3089
4.6453 1996
1994 1997
1996 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Waibel
Memory,
Kohonen
Xu L, A,Teuvo,
1994, V,1989,
P Ieee
Neural 1989, T Acoust
Self
Networks, Org Speech,
Ass
V7, P609 V37, 1989
1989
1994 5.2033
5.3089
4.3694 1994
1996
1995 1997
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Jacobs
P328
Waibel
Memory,
Xu L, Ra,
A,Teuvo,
1994, 1988,
1989,
V, Neural
P Ieee
Neural Networks,
T Acoust
Networks, Speech,V1, P295
V37, 1989
1988
1989 5.2033
4.6453
5.2033 1994
1994 1997
1996
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Kohonen Teuvo,Kohonen
P328
P3281989,
Jacobs
Waibel
Memory, Ra,
A,V, SelfP Org
1988,
1989, 1989,
Neural
Ieee TAssSelf OrgV7,
Networks,
Acoust AssP609
Speech,V1, V37,
P295 1994
1989
1988
1989 4.3694
5.3089
4.6453
5.2033 1995
1996
1994 1998
1997
1996
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Xu L,
Jacobs
P328 1994,
Ra, Neural
1988, Networks,
Neural V7, P609
Networks, V1,V3,
P295
1989 1994
1989
1988
5.30894.3694
4.6453 1995
5.3089 19961994
1996 1998
1997
1996
1997 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Waibel
Bishop
Memory,
Xu A,V,
C,
L, 1994,
Jacobs Ra, 1989,
1991,
Neural
1988, IeeeNetworks,
P Neural
Neural T Acoust Speech,
Computation,
V7,
Networks, P609
V1, V37,
P295 1989
1994
1988 5.2033
4.3694
4.6453 1994
1995
1994 1997
1998
1996 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Memory, V, P Bishop
P328
Waibel C,
A, 1991,
1989, Neural
Ieee Computation,
T Acoust Speech, V3,
V37, 1989
1991 5.2033
4.0149 1994 1997 ▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Xu L,
Jacobs
Jacobs
P328 1994,
Ra,
Ra, Neural
1988,
1988, Networks,
Neural
Neural V7,
Networks,
Networks, P609
V1,
V1, P295
P295 1994
1988
1988
1991 4.3694
4.6453
4.6453
4.0149 1995
1994
1994
1995 1998
1996
1996 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P579
Bishop
Waibel
Xu L,
Jacobs C,
A,
1994,
Ra, 1991,
1989,
Neural
1988, Neural
Ieee T Computation,
Acoust
Networks,
Neural Speech,
V7,
Networks, P609
V1, V3,
V37,
P295 1989
1994
1988 5.2033
4.3694
4.6453 1994
1995
1994 1997
1998
1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P579
P328
Bishop
Xu C, 1991,
L, 1994, Neural Neural Computation,
Networks, V7, P609 V3, 1991
1994
1989 4.0149
4.3694
5.2033 1995
1994 1996
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Jacobs
P579
Baum
Bishop
P328
Xu ERa,
L, 1994, 1988,
C,B,1991,
1989,
Neural Neural
Neural
Neural Networks,
Computation,
Computation,
Networks, V1,V3,
V7, P609 P295
V1, 1988
1991
1994 4.6453
4.0149
4.3694 1994
1995
1995 1996
1996
1998 ▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Jacobs
Baum
Xu
P579L, ERa,
1994, 1988,
B, 1991,
1989,
Neural Neural Networks,
Computation,
Networks, V7, V1,V3,
P609 P295
V1, 1988
1989
1994
1991 4.6453
3.9806
4.3694
4.0149 1994
1996
1995 1996
1997
1998
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Bishop
Xu L,
Jacobs C,
1994,
Ra, Neural
1988, Neural
Neural Computation,
Networks, V7,
Networks, P609
V1, P295 1994
1989
1988 4.3694
3.9806
4.6453 1995
1996
1994 1998
1997
1996 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P151
Baum
P579
Bishop
Xu L, EC,
1994,B,1991,
1989,
Neural Neural
Neural Computation,
Computation,
Networks, V7, P609 V1,
V3, 1991
1994 4.0149
4.3694 1995 1996
1998 ▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P151
Jacobs
Baum
Bishop
P579 ERa, 1988,
C,B,1991,1989, Neural
Neural
Neural Networks,
Computation,
Computation, V1,V3,P295
V1, 1989
1991
1988 3.9806
4.0149
4.6453 1996
1995
1994 1997
1996
1996 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Xu
P151
P579
Baum L,
Bishop 1994,
EC, B,1991,Neural
1989, Networks,
Neural
Neural V7,
Computation,
Computation, P609 V3,
V1, 1994
1989
1991 4.3694
3.9806
4.0149 1995
1996
1995 1998
1997
1996 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Bishop
Ritter H,C,
Xu L, 1994, 1991,
1992, Neural Neural
Neural Computation,
Networks, V7, P609
Computation S,V3,
V, P 1994
1992
1991 4.3694
3.7901
4.0149 1995
1995 1998
1996 ▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P151
P579
Baum
Bishop
Xu EC,
L, 1994,
Ritter H, B,
1992,1989,
1991,
Neural Neural
Neural
Neural Computation,
Computation,
Networks, V7, P609
Computation V1,
S,V3,
V, 1989
1991
1994 3.9806
4.0149
4.3694 1996
1995
1995 1997
1996 ▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P579
P151
Baum
P579
Bishop EC, B, 1989,
1991, Neural
Neural Computation,
Computation, V1,P
V3, 1992
1991
1989 3.7901
4.0149
3.9806 1996
1995
1996 1998
1996
1997 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Ritter
Xu
Baum
P579
P151L,
Bishop H,
1994,
EC, 1992,
B, 1991, Neural
Neural
1989, Neural Computation
Networks,
Neural Computation,V7,
Computation, V3,S,
P609 V, P
V1, 1992
1994
1989
1991 3.7901
4.3694
3.9806
4.0149 1996
1995
1995 1998
1997
1996 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Baum
P151
Baum
P579 E
Ritter H,
E B,
B, 1989,
1992,
1989, Neural
Neural
Neural Computation,
Computation
Computation, S, V1,
V, P
V1, 1992
1989 3.7901
3.9806 1996
1996 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Bishop
Battiti
Ritter
P151
Baum H,
E C,
R, 1991,
1992,
1992,
B, 1989, Neural
Neural
Neural
Neural Computation,
Comput,
Computation
Computation, S,V3,
V4, P141 V,
V1,P 1991
1992
1989
1992
1989
4.0149
3.5404
3.9806
3.7901
3.9806
1995
1994
1996
1996
1996
1999
1997
1998
1997 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P579
Battiti
BishopH,R, 1992, Neural Comput, V4, P141 1992
1991 3.5404
4.0149 1994
1995 1999
1996 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P151
Ritter
P151
Baum
P579 ER,C,
BattitiH,
Ritter B, 1991,
1992,
1989,
1992,
1992,
Neural
Neural
Neural
Neural
Neural
Computation,
Computation
Computation,
Comput,
Computation
S,V3,
V4, P141
S,
V, P
V1,
V, P
1992
1989
1992
1991
1992
3.7901
3.9806
3.5404
4.0149
3.7901
1996
1994
1995
1996
1998
1997
1999
1996
1998
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P151
BaumH,
Barnard
P579
Battiti E
R, B,
E, 1989,
1992,
1992, Neural
Ieee
Neural T Computation,
Neural
Comput, Networ,
V4, P141V1,
V3, 1989
1992 3.9806
3.5404 1996
1994 1997
1999 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Ritter
P151
Barnard
Baum E 1992,
E, 1992, Neural Computation
Ieee TComput,
Neural Networ,S, V, P
V3, 1992
1989 3.7901
3.9806 1996
1996 1998
1997 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Battiti
Ritter
Ritter
P151 R,B,
H,
H, 1989,
1992,
1992, Neural
Neural
Neural Computation,
Computation
Computation S, V1,
V4, P141
S, V,
V, P
P 1992
1992 3.5404
3.7901
3.7901
3.5404 1994
1996
1996
1994 1999
1998
1998
1999 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P232
Barnard
Baum
BattitiH,
Ritter E E,
B, 1992,
1989, Ieee
Neural
R, 1992, Neural ComputationT Neural Networ,
Computation,
Comput, V4, P141 S, V3,
V1,
V, P 1989
1992 3.9806
3.5404
3.7901 1996
1994
1996 1997
1999
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P232
P151
Barnard
Battiti R, E,1992,1992, Ieee TComput,
Neural Neural Networ,
V4, P141 V3, 1992
1989 3.5404
3.9806 1994
1996 1999
1997 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Ritter
P232
Ku
Barnard
P151
Battiti H,
Cc,R, E,1992,
1995, 1992,
1992, Neural
Ieee Ieee
Neural Computation
T Neural
TComput,Networ,
Neural Networ,
V4, S, V,
V6, V3,
P141 P 1992
1992
1992 3.7901
3.5404
3.5404 1996
1994
1994 1998
1999
1999 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Ritter
Ku H,
Cc,R, 1995,1992, Neural
Ieee Computation
T Neural Networ, S, V, P 1992 3.7901 1996 1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Battiti
P232
Barnard
Battiti
Ritter
P144
Ku Cc,H,R, E,1992,
1992,
1995, 1992, Ieee
Neural
Neural
Ieee
Comput,
TComputation
Neural
Comput,
T Neural V4, V6,
V4,
Networ,
P141
Networ,
S, V,V3,
P141
V6, P
1995
1992
1992
1995
1992
3.521
3.5404
3.5404
3.521
3.7901
1997
1994
1994
1997
1996
2000
1999
1999
2000
1998
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P302
Chen
Poggio
P281
Moody S,T,
J,1991,
1990,
1989, IEEE T Neural
P IEEE,
Neural Networ, V1,
V78, P1481
Computation, V2, 1991
1990
1989 7.2449
7.4954
7.2193 1996
1995 1999
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Chen
P302
Poggio
P281
Moody
Pao S, J,
Y-H, 1991,
T, 1990,
1989, IEEE
NeuralT Neural
P IEEE,
Adaptive V78, Networ,
P1481
Computation,
Pattern V2,
Rec, V1,
V, P 1991
1990
1989 7.2449
7.4954
7.2193
7.1573 1996
1995
1995
1994 1999
1998
1997 ▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P302
Moody
Chen
Poggio
P281
Pao Y-H, J,1991,
S,T, 1989,
1990,
1989, Neural
IEEE
P IEEE,
Adaptive Computation,
T Neural
V78, P1481
Pattern Rec, V1,
Networ, V2,
V, PP 1991
1990
1989 7.2449
7.4954
7.2193
7.1573 1996
1995
1994 1999
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P302
Chen
Moody
Pao
P281 S,
Y-H, 1991,
J, 1989, IEEE
NeuralT
Adaptive Neural Networ,
Computation,
Pattern Rec, V2,
V1,
V, 1991
1989 7.2449
7.2193
7.1573 1996
1995
1994 1999
1997 ▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P302
P281
Chen
Moody S,J,1991,
1989, IEEE
Neural T Neural Networ,
Computation,
Pao Y-H, 1989, Adaptive Pattern Rec, V, V2,
V1, P 1991
1989 7.2449
7.2193
7.1573 1996
1995
1994 1999
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P302
Moody
P281
Chen
Pao S, J,1991,
Y-H,
Kohonen 1989,
T, 1990, Neural
IEEE TIEEE,
Adaptive
P Computation,
Neural Rec, V1,
Networ,
Pattern
V78, P1464 V2,
V, P 1991
1989
1990 7.2449
7.2193
7.1573
6.3202 1996
1995
1994
1996 1999
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P302Y-H,
P281
Moody
Pao
Kohonen J, 1989,
T, 1990,
1990, Neural
Adaptive
P IEEE,
IEEE,Computation,
Pattern Rec, V1,
V78, P1464
P1464 V, PP 1991
1989
1990 7.2193
7.2449
7.1573
6.3202 1995
1996
1994 1999
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Pao
P281Y-H,
Moody
Kohonen
P302 J, 1989,
T, Adaptive
Neural
P Pattern
Computation,
V78, Rec, V,
V1, 1989
1990 7.1573
7.2193
6.3202 1994
1995
1996 1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P281
Kohonen
Pao
MoodyY-H,J,ST,
Fahlman E,1990,
1989,
1989, P Adv
IEEE,
Adaptive
Neural
1990, V78, P1464
Pattern
Computation,
Neural Rec, V,
V1,P
Informati, 1990
1989 6.3202
7.1573
7.2193 1996
1994
1995 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Pao
P281
Moody Y-H,
Kohonen
Fahlman J, 1989,
T,
S1989,1990,Adaptive
E, 1990, P
Neural
1990, IEEE, Pattern
V78, Rec,
P1464
Computation,
Adv Neural V,
V1,
Neural Informati,
Informati, P 1989
1989
1990 7.1573
7.2193
6.3202 1994
1995
1996 1997
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Pao
P281 Y-H, S
Fahlman
Kohonen
V2, P524 T,E,1990,
1990, Adaptive
IEEE,Pattern
PAdv Rec, V, P
V78, P1464
P1464 1989
1990 7.1573
7.2193
6.3202 1994
1995
1996 1997
1998 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Kohonen
Pao
Fahlman
P281
V2, P524 T,
Y-H, S1989, E, 1990, P
AdaptiveIEEE,
Adv V78,
Pattern
Neural Rec, V, P
Informati, 1990
1989 6.3202
7.1573 1996
1994 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Kohonen
Pao
V2, P524
Fahlman
Narendra T,
Y-H, S1989, E,1990,
KE, 1990,
S,1990,
1990,P Adv
AdaptiveIEEE, V78, P1464
Pattern
Neural
IeeeNeural
Trans Rec, V, P
Informati,
Neural 1990
1989 6.3202
7.1573 1996
1994 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Kohonen
Publications 2018,V2,
FahlmanY-H,ST,
6,P524
Pao 32
Narendra KE, 1990,
1989,
S,1990,
1990,PAdv
IEEE,
Adaptive V78, P1464
Pattern
IeeeNeural
Trans Rec, V, P
Informati,
Neural 1990
1989
1990 6.3202
7.1573
6.2445 1996
1994
1995 1998
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
18 of 22
Fahlman
Kohonen
V2,
Pao
Netw, P524
Narendra
Y-H,V1,SS1989,
T,
KP4 1990,
S, 1990,PAdv
AdaptiveIEEE,
Ieee Trans
Pattern Informati,
V78, P1464
Neural
Rec, V, P 1989
1990 7.1573
6.3202
6.2445 1994
1996
1995 1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Kohonen
Fahlman
Narendra
V2,
Netw, P524 T,
K
V1,ST,P4E,
P4 1990,
S,1990,
1990, P IEEE,
Adv
Ieee V78,
Neural
Trans P1464
Informati,
Neural 1990 6.3202
6.2445 1996
1995 1998 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
V2,
Netw, P524
Fahlman
Kohonen
Narendra V1, KE,S,1990,
1990,1990,P Adv
IEEE,
Ieee Neural
V78,
Trans Informati,
P1464
Neural 1990 6.3202
6.2445 1996
1995 1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Funahashi
Fahlman
V2,
Netw, V1,ST,
P524
Kohonen
Narendra K K,
E,S,
P4 1989,
1990,
1990,
1990, Neural
PAdv
IEEE, Networks,
Neural
V78,
IeeeNeural
Trans P1464
Neural V2,
Informati, 1990
1990 6.3202
6.3202
6.2445 1996
1996
1995 1998
1998 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Funahashi
V2, P524
Fahlman
Narendra
Kohonen
Netw,
Funahashi V1,ST,K K,
P4
K, 1989,
E,1990,
S,1990,
1990,
1989, Neural
PAdvIeee
IEEE,
Neural Networks,
Trans
V78, V2,
Informati,
Neural
P1464
Networks, V2, 1989
1990
1990 5.8544
6.3202
6.2445 1994
1996
1995 1997
1998
1998 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P183
V2, P524
Fahlman
Narendra
Funahashi SK E,S,1990,
K, 1990,Adv
1989, IeeeNeural
Neural Trans Informati,
Neural
Networks, V2, 1989
1990
1989 5.8544
6.3202
6.2445
5.8544 1994
1996
1995
1994 1997
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Netw,
P183 V1, P4 ▂▂▂▂▂▂▂▂
Netw,
V2,
Fahlman
Narendra
P183
FunahashiV1,SK
P524 P4E,S,1989,
K, 1990,
1990, Adv
Ieee
Neural Neural
Trans Informati,
Neural
Networks, V2, 1990
1989 6.3202
6.2445
5.8544 1996
1995
1994 1998
1997 ▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Rumelhart
V2,
Netw, P524
Narendra
Fahlman
P183
Funahashi
Rumelhart V1,SK De,
P4
E,
K,
De,
1986,Neural
S,1990,
1990,
1986,Adv
1989, Parallel
Ieee Distributed,
Trans
Neural
Parallel Neural
Informati,
Networks,
Distributed,V2, Table
1990
1989
1986
Cont.
1990 8. 6.2445
6.3202
5.8544
5.4868 1996
1995
1994
1992 1998
1998
1997
1994 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V2, PP524
Netw,
Funahashi
Narendra
P183
Rumelhart V1, K P4
K,S,1989,
De, 1990,
1986, Neural
Ieee
ParallelNetworks,
Trans NeuralV2,
Distributed, 1990
1989
1986 6.2445
6.3202
5.8544
5.4868 1995
1996
1994
1992 1998
1997
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V1,
Netw,
Narendra
V2, P524
Funahashi
Rumelhart V1, KP4
K,S,
De, 1990,
1989,
1986, Ieee
Neural Trans
Parallel Neural
Networks,
Distributed,V2, 1989
1990
1986 5.8544
6.2445
5.4868 1994
1995
1992 1997
1998
1994 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P183
V1,
Netw,
P183 P V1, P4
Narendra
Funahashi K
K, S,1989,
1990, Ieee
Neural Trans NeuralV2,
Networks, 1990
1989 6.2445
5.8544 1995
1994 1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
V1, P
Rumelhart
Kohonen De,
Teuvo, 1986,
1989, Parallel
Self Distributed,
Org Ass 1986 5.4868 1992 1994 ▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Netw,
P183P V1,Teuvo,
Funahashi
Narendra
V1,
Rumelhart
Kohonen KP4
K,S,1989,
De, 1990,
1986, Neural
1989,Ieee Networks,
Trans
Parallel
Self Neural
Distributed,
Org Ass V2, 1990
1989
1986
1989 6.2445
5.8544
5.4868
5.3089 1995
1994
1992
1996 1998
1997
1994
1997 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
References
Netw,
P183 P V1,Teuvo,
Funahashi P4
K, Year Strength
1989 5.8544 Begin1994 End
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
1992–2018
Rumelhart
V1,
Kohonen
Memory,
P183
Funahashi V, K,P1989,
De, 1986, Neural
1989, Self Networks,
ParallelOrg Ass V2,
Distributed, 1990
1986
1989
1989
1986
6.2445
5.4868
5.3089
5.8544
5.4868
1995
1992
1996
1994
1992
1998
1994
1997
1994 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Netw,
V1,
P183 P V1,Teuvo,
Rumelhart
Kohonen
V1,
Memory,
P
Funahashi
Rumelhart V,P4 P1989,
De,
K,
De,
1986,
1989,
1986,
Neural
1989, Parallel
Neural
Parallel
Networks,
Self Org Ass V2,
Distributed,
Networks,
Distributed, V2, 1986
5.3089
5.8544
5.4868
1996
1994
1992
1997
1994
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Memory,
Kohonen
Waibel A, V, P
Teuvo,
1989, 1989,
Ieee T Self Org
Acoust Ass V37,
Speech, 1989 5.3089 1996 1997 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Waibel A, 1989, V1,Ieee
P183
Rumelhart
P
Funahashi
Memory,
Kohonen
Waibel T Acoust
V, De,
K,
A,Teuvo, P
Teuvo,
1989, 1986,
1989, Speech,
1989,
Ieee Parallel
Neural
T Distributed,
Networks,
Self Org
AcoustOrg Ass V37,
Speech, V2, 1989
1986
1989
1989 5.8544
5.4868
5.3089
5.2033 1994
1992
1996
1994 1997
1994
1997
1997 ▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P183
V1, P A,
Kohonen
Rumelhart
Memory,
Waibel
P328 V, De,
P 1986,
1989, 1989,
Ieee T Self
Parallel
Acoust Ass
Distributed,
Speech, 1989
V37, 5.20335.3089
1986
1989
1989 5.4868
5.8544
5.2033 19941996
1992
1994
1994 1997
1994
1997
1997 ▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V37, P328 V1,
P183 P A,V,
Rumelhart
Kohonen
Waibel
Memory,
P328 De,
P 1986,
Teuvo,
1989, 1989,
Ieee TParallel
Acoust Distributed,
Self Org Ass V37,
Speech, 1986
1989 5.4868
5.3089
5.2033 1992
1996
1994 1994
1997 ▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V1,
P328
WaibelP A,V,
Memory,
Rumelhart
Kohonen P
De,
Teuvo,
1989, 1986,
1989,
Ieee TParallel
Self Org
Acoust Distributed,
Ass V37,
Speech, 1986
1989 5.4868
5.3089
5.2033 1992
1996
1994 1994
1997 ▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V1,
P328
Waibel
JacobsP Ra,
Kohonen
Memory,
Rumelhart Teuvo,
V, P 1986,
De,
A,Teuvo,
1989,
1988, 1989,
Ieee
Neural Self
Parallel
T AcoustOrg AssV1, V37,
Distributed,
Speech,
Networks, P295 1986
1989
1988 5.4868
5.3089
5.2033
4.6453 1992
1996
1994 1994
1997
1996 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V1, P Ra,
Memory,
Kohonen
Waibel
P328
Jacobs A, V, P Ieee
1989,
1988, 1989,
Neural T Self
AcoustOrgSpeech,
Networks, AssV1, V37,
P295 1989
1986
1989
1988 5.3089
5.4868
5.2033
4.6453 1996
1992
1994 1997
1994
1997
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Jacobs Ra, 1988, Neural
Memory,
Kohonen
V1,
Waibel
Jacobs
P328 P Ra, V, Networks,
A,Teuvo, P Ieee
1989,
1988, 1989,
Neural V1,Org
Self
T Acoust P295 1988
AssV1, V37,
Speech,
Networks, P295 4.64535.2033
1989
1988 5.3089
4.6453 19941994
1996 1996
1997
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Memory,
P328
Kohonen
Waibel A, V, P
Teuvo,
1989, 1989,
Ieee
Jacobs Ra, 1988, Neural Networks, T Self
Acoust Org AssV1, V37,
Speech, P295 1989
1988 5.3089
5.2033
4.6453 1996
1994 1997
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Memory,
Waibel
P328
Kohonen
Jacobs
Xu L, A,V,
Ra,
1994, P Ieee
1989,
Teuvo,
1988,
Neural 1989,
Neural T Acoust
Self
Networks, Speech,
OrgV7,
Networks, V1, V37,
AssP609 P295 1989
1989
1988
1994 5.3089
5.2033
4.6453
4.3694 1996
1994
1995 1997
1997
1996
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Memory,
P328
Waibel
Jacobs
Xu A, V,
Ra,
L, 1994,
1994, P Ieee
1989,
1988,
Neural Neural T Acoust Speech,
Networks,
Networks, V7, V1, V37,
P609 P295 1989
1988
1994 5.2033
5.3089
4.6453
4.3694 1996
1994
1995 1997
1996
1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Jacobs
P328
Waibel
Xu L,
Memory,
Xu L, 1994, Neural Ra,
A,V, 1988,
1989,
Networks, P Ieee
Neural Neural
V7, Networks,
T Acoust
Networks,
P609 V7, V1,
Speech,
V7, P609 P295
V37,
1994 1988
1989
1994
4.36944.6453
5.2033
4.3694 1994
1995 1996
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P328
Xu L, 1994,
Jacobs
Waibel
Bishop Ra,
A,1991,
C, Neural
1988,
1989, Ieee
NeuralNetworks,
Neural Networks,
T Acoust P609
V1,V3,
Speech,
Computation, P295
V37, 1994
1988
1989 4.6453 19951995
4.3694
5.2033 1994 1998
1998
1996
1997 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Jacobs
P328
Xu L,
Waibel
Bishop Ra,
1994,
A, 1988,
Neural
1989,
C, 1991,
1991, Neural
Ieee
Neural Networks,
Networks,
T Acoust V7, V1,
P609
Speech,
Computation, P295
V37,
V3, 1988
1989
1994
1991 4.6453
5.2033
4.3694
4.0149 1994
1994
1995 1996
1997
1998
1996 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Jacobs
P328
Bishop
Xu
P579 L, Ra,
C,
1994, 1988,
Neural Neural
Neural Networks,
Computation,
Networks, V7, V1,
P609 P295
V3, 1988
1989
1994
1991 4.6453
5.2033
4.3694
4.0149 1994
1995 1996
1997
1998
1996 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Bishop C, 1991, Xu L, 1994,
Jacobs
Bishop
P328
Neural
P579 Ra,
C, 1991,Neural
1988, Neural
Computation, Networks,
Neural V7, P609
Networks,
Computation, V1,V3,
P295 1994
1988
1991 4.3694
4.6453
4.0149 1995
1994 1998
1996 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Xu
P579 L, 1994,
Jacobs
Bishop
Baum ERa,
C, Neural
1988,
1991,
B,1991,
1989, NeuralNetworks,
Neural
Neural V7, P609
Networks,
Computation,
Computation, V1,V3,
P295
1991
V1, 1994
1991
1988 4.3694 19951995
4.01494.0149
4.6453 1994 1998
1996
1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
V3, P579 Xu
P579 L, 1994,
Jacobs
Bishop
Baum E Ra,
C,B, Neural
1988,
Neural
Neural V7, P609
Networks,
Computation,
Computation, V1,V3,P295
V1, 1994
1988
1991
1989 4.3694
4.6453
4.0149
3.9806 1995
1994
1996 1998
1996
1996
1997 ▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
Bishop
Xu
P579
Baum
Jacobs
P151 C,
L, 1994,
ERa,B,1991,
Neural
1989,
1988, Neural
Neural Computation,
Networks,
Computation,
Networks, V1,V3,
V7, P609 V1,
P295 1994
1988
1991
1989 4.3694
4.6453
4.0149
3.9806 1994
1995
1996 1998
1996
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Xu L, 1994,
Bishop
Baum
P579
P151 EC, Neural
B, 1991,
Neural V7, P609V3,
Computation,
Computation, V1, 1991
1994
1989 4.0149
4.3694
3.9806 1995
1996 1996
1998
1997 ▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
P579
Bishop
Xu
P151
Baum L, E C,
1994,B, 1991,
Neural
1989, Neural
Neural Computation,
Networks, V7,
Computation, P609 V3,
V1, 1991
1994
1989 4.0149
4.3694
3.9806 1995
1996 1996
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
Baum E B, 1989, XuNeural
Bishop
P579
P151
Baum
RitterL, H,C,
1994,
EC, B,1992,Computation,
1991,
Neural
1989, Neural
Neural
Neural Computation,
Networks, V7, P609
Computation,
Computation S,V3,
V1,
V, P 1991
1994
1989
1992 4.0149
4.3694
3.9806
3.7901 1995
1995
1996 1996
1998
1997
1998 ▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
P579
Baum
Bishop
Xu
P151 E B,
L, 1994,
Ritter H, 1989,
1991,
1992,Neural Neural
Neural
Neural Computation,
Computation,
Networks, V7, P609
Computation 1989
V1,
S,V3,
V, P 3.98063.7901
1991
1994
1989
1992 4.0149
4.3694
3.9806 19961996
1995 1997
1996
1998
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V1, P151 P579
Bishop
Baum H,
Ritter
P151 EC, B, 1991,
1989,
1992, Neural
Neural
Neural Computation,
Computation,
Computation S, V3,
V1,P
V, 1991
1989
1992 4.0149
3.9806
3.7901 1995
1996 1996
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P579
P151
Bishop
Baum
Ritter E C,
H, B, 1991,
1989,
1992, NeuralComputation
Neural Computation, S, V3,
V1,P
V, 1991
1989
1992 4.0149
3.9806
3.7901 1995
1996 1996
1997
1998 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
P579
Baum
P151 H,
Bishop
Ritter
Battiti E C,
R, B, 1989,
1991,
1992, Neural
Neural
Neural Computation,
Computation,
Computation
Comput, V1,
S,V3,
V4, P141 V, P 1991
1989
1992 4.0149
3.9806
3.7901
3.5404 1995
1996
1994 1996
1997
1998
1999 ▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
P579
P151
Baum
Ritter
Battiti E
R,B,
H, 1989,Neural
1992, NeuralComputation
Computation,
Comput, V4, S, V1,
P141V, P 1989
1991
1992 3.9806
4.0149
3.7901
3.5404 1995
1996
1994 1997
1996
1998
1999 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Ritter H, 1992,Ritter
Neural
P151
Baum
Battiti
P579 H,
E
R, B, Computation
1992,
1989, Neural
Neural S, V, V4,
Computation P P141
Computation,
Comput, S, 1992
V,
V1,P 3.79013.7901
1992
1989 3.9806
3.5404 19961996
1994 1998
1998
1997
1999 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P151
Battiti
Ritter
Baum
Barnard R,
H,
E 1992,
B,
E, 1989,
1992, Neural
Neural
Ieee TComput,
Computation V4,
Computation,
Neural P141
Networ,S, V,
V1,P
V3, 1992
1989 3.5404
3.7901
3.9806 1994
1996 1999
1998
1997 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Ritter
P151
Battiti E
Baum
Barnard H,
R,B,1992,
E, 1989,
1992, Neural
Neural
Ieee T Computation
Comput, S,
V4, P141
Computation,
TComputation
Neural Networ, V,
V1,P
V3, 1992
1989
1992 3.7901
3.9806
3.5404 1996
1996
1994 1998
1997
1999 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
Ritter
P151 H,
Barnard
Battiti
P232 R, E, 1992,
1992, Neural
Ieee Neural
Comput, Networ,
V4, S, V,
P141 P
V3, 1992
1989
1992 3.7901
3.9806
3.5404 1996
1994 1998
1997
1999 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Battiti
Ritter
Battiti R, 1992,Barnard
P151
Neural
P232 R,E,
H, 1992,
1992,
Comput, Neural
Ieee T Comput,
Computation
Neural
V4, V4, P141
P141Networ, S, V, P
V3,
1992 1992
3.54043.5404
3.7901 19941994
1996 1999
1998
1999 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Battiti
Ritter
P232 Cc,H,
Barnard
Ku R, 1992,
E,
1995, 1992,
IeeeNeural
Ieee Comput,
TComputation
T Neural Neural V4, P141
S, V,
Networ,
Networ, V6, P
V3, 1992 3.5404
3.7901 1994
1996 1999
1998 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
Battiti
P232
Ritter
Barnard
Ku R,
Cc,H,H, 1992,
E,
1995,1992,
1992,
IeeeNeural
Neural
Ieee TComput,
T Neural
NeuralComputation
Neural V4, P141
Networ,
Networ, S, V,
V6, V3,P 1992
1992
1995 3.5404
3.7901
3.521 1994
1996
1997 1999
1998
2000 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
Barnard
Battiti
P232
Ku Cc,
Ritter
P144 R, E,
1995, 1992,
1992, Ieee Ieee
T
Neural T Neural
Comput, Networ,
V4,
Networ,
Computation P141
V6,
S, V3,
V, P 1992
1995 3.7901
3.5404
3.521 1996
1994
1997 1998
1999
2000 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Barnard E, 1992,Battiti
Barnard
Ku
P232
P144 Ieee
Cc, R, 1992,
E,
T
1995, 1992,
Neural
IeeeNeural
Ieee
T TComput,
Neural
Networ,
Neural V4, P141
Networ,
Networ, V6, V3, 1992
1995 3.5404
3.521 1994
1997 1999
2000 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
P232
Barnard
Battiti
P144
Ku R, E,
Cc, 1995, 1992,
1992, Ieee
Neural
IeeeIeee T
T Neural Neural
Comput, Networ,
V4,
Networ, P141 V3,
V6,1992 1992
1995 3.5404
3.54043.5404 1994
3.521 19941997 1999
2000
1999 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V3, P232 Barnard
P232
Battiti
P144
Ku Cc, R,
Rumelhart E,1992,
1995, 1992,
De,Ieee Neural T Comput,
T Neural
1986, Neural Neural
Nature, Networ,
Networ,V4,P533
V323, P141
V6, V3, 1992
1992
1995
1986 3.5404
3.521
3.4325 1994
1994
1997
1993 1999
1999
2000
1994 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P232
Barnard
Ku
P144 Cc,
Battiti
Rumelhart E,
1995,
R, 1992,
1992,
De,Ieee Ieee
T
Neural
1986, TComput,
Neural
Nature, Networ,
Networ, V6,
V4,P533
V323, P141 V3, 1992
1995
1986 3.5404
3.521
3.4325 1994
1997
1993 1999
2000
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P232
Barnard
Ku Cc, 1995,
Rumelhart
P144 E, 1992,
De,Ieee Ieee
1986, T Neural
T Neural
Nature, Networ,
Networ,
V323, V6, V3,
P533 1992
1995
1986 3.5404
3.521
3.4325 1994
1997
1993 1999
2000
1994 ▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P144
P232
Barnard
Ku Cc,
Rumelhart
Ku Cc, 1995, Ieee
Drago T Neural
Gp, E,
1995, 1992,
De,Ieee
1992, Ieee
T
1986,
Networ,
Ieee T
Neural Neural
Nature,
T Neural Networ,
Networ,
V323, V6,
P533
Networ, V3,
V3, 1992
1995
1986 3.5404
3.521
3.4325 1994
1997
1993 1999
2000
1994 ▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
P232
Ku
P144 Cc,
Barnard
Rumelhart 1995,
E, 1992,Ieee
1992,
De, T Neural
Ieee
1986, Networ,
T Neural
Neural
Nature, V6, V3,
Networ,
V323, P533 V3, 1992
1995
1986 3.5404
3.4325 1994
3.521 19971997
1993 1999
2000
1994 ▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▃▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
V6, P144
Drago
P232
P144
Ku
Drago
Rumelhart
P627
Gp,
Cc, Gp,
1995, Ieee
1992,
De,
Ieee
Ieee
1986,
T
T Neural
T
Nature, Networ,
Neural V6,1995
Networ,
Networ,
V323, P533 V3, 1992
1995
1992
1986
1992
3.5213.5404
3.4191
3.521
3.4325
3.4191
1996
1997
1994
1993
1996
2000
2000
2000
1999
1994
2000 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
P144
Ku
P232
Drago
P627 Cc,Gp,
1995, De, 1986,
IeeeIeee
1992, Nature,
T Neural
T Neural V323,
Networ, P533
Networ,V6, V3, 1986
1995
1992 3.4325
3.521
3.4191 1993
1997
1996 1994
2000 ▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P144
Rumelhart
Ku Cc,Gp,
P627
Drago 1995, De, 1986,
Ieee
1992, Nature,
T Neural
Ieee T Neural V323,
Networ, P533
V6,V3,
Networ, 1986
1995
1992 3.4325
3.521
3.4191 1993
1997
1996 1994
2000 ▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
Rumelhart
P144
P627
Ku
DragoCc,F,
Girosi 1995,
Gp, De,Ieee
1992,
1995, 1986, Nature,
T Neural
Ieee
Neural TComput, V323,
V7, P533
Networ,
Neural V6, V3,
Networ,
P219 1986
1995
1992
1995 3.4325
3.521
3.4191 1993
1997
1996 1994
2000
2000 ▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▂▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
Rumelhart De,Drago
Rumelhart
P144
P627
1986,
Girosi Gp,
F, 1992,
De,Neural
Nature,
1995, Ieee
1986,V323,T Neural
Nature,
P533
Comput, Networ,
V323,
V7, P533
P219 V3,
1986 1986
1992 3.4325 1993
3.521 19931997
3.43253.4191
1995 3.4191 1996 1994
2000
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Rumelhart
Drago F,
Girosi
P144
P627 Gp, De, Neural
1992,
1995, 1986,
Ieee Nature,
TComput,
Neural V323,
V7, P533
Networ,
P219 V3, 1992
1986
1995 3.4325 1996
1993 2000
1994 ▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
P627
Drago
Rumelhart
Girosi
Kohonen Gp,
F, 1992,
De,
1995,
T, Ieee
1986,
Neural
1988, Self TComput,
Neural
Nature,
Org Ass Networ,
V323, P219V3,
V7, P533
Memory, V, 1992
1986
1995 3.4325
3.4191 1993
1996 1994
2000 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Drago
P627
RumelhartGp,
Girosi F, 1995,
Kohonen T, 1992,
De,
1988, Ieee
1986,
Neural
Self T Neural
Nature,
Comput,
Org Ass Networ,
V7, P219V3,
V323, P533
Memory, V, 1992
1986
1995
1988 3.4191
3.4325
3.3453 1996
1993
1995 2000
1994
1996 ▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Drago Gp, 1992, P627
Drago
Kohonen
Rumelhart
P Ieee Gp,
F, T 1992,
T,De,1988, Ieee
1986,Self T Neural
Org
Nature, Ass Networ,
Memory,
V323, V3,
P219 V,
V7, P533 1992
1986 3.4191
3.4325 1996
1993 2000
1994 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
T,Neural Networ, ▂▂▂▂▂▂▂▂
Girosi 1995, Neural Comput, 1995
1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
Girosi
P627
Drago
Kohonen
P F,
Gp, 1995,
1992, Neural
1988, Ieee
Self Comput,
TOrg
Neural V7, P219
Networ,
Ass Memory, V3,
V,
1992 1995
1992
1988
3.41913.4191
3.3453 19961996
1995 2000
1996
2000 ▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
V3, P627 P627
Girosi
PDragoF,
Kohonen
Broomhead Gp,1995,
T,1992,
1988,
D Neural
S, Ieee Comput,
Self TOrg
1988, Neural V7, P219V3,
Networ,
Ass Memory,
Complex Systems, V, 1995
1992
1988 3.4191
3.3453 1996
1995 2000
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Girosi
P627
P
Drago
Kohonen
Broomhead F,
Gp, 1995,
T,1992,
1988,
D Neural
S, Ieee Comput,
SelfTOrg
1988, Neural
Org V7, P219V3,
Ass Networ,
Complex Memory,
Systems, V, 1995
1992
1988
1988 3.4191
3.4191
3.3453
3.3453 1996
1996
1995
1995 2000
2000
1996
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Kohonen
Girosi
PP627
Broomhead
V2, P321 T,
F, 1995, 1988,
D S, Self
Neural
1988, Ass
Comput,
Complex Memory,
V7, P219 V,
Systems, 1995
1992
1988 3.4191
3.3453 1996
1995 2000
1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Girosi
Kohonen
P627
Broomhead
P
V2, F,
P321 1995,
T, 1988,
D Neural
S, Self
1988, Comput,
Org Ass
Complex V7, P219
Memory,
Systems, V, 1988
1995 3.3453
3.4191 1995
1996 1996
2000 ▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
P
Kohonen
Girosi
V2,
Girosi F, 1995,V2, P321
Neural T, 1988,
F, 1995,
Comput, SelfV7,
Neural Org Ass Memory,
Comput,
P219 V7, P219 V,
1995 1988
1995 3.3453
3.4191
3.41913.3453 1995
1996 1996
2000 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
3.419119961995 2000
Broomhead D S, 1988, Complex Systems, ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Kohonen
PGirosi
P321
Broomhead T, D
F, 1995, 1988,
S, Self Org
Neural
1988, Ass Memory,
Comput,
Complex V7, P219
Systems, V, 1988
1995 1996 1996
2000 ▂▂▂▂▃▃▃▃▃▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P
Kohonen
Broomhead
Girosi
V2, P321 T, D
F, 1995, 1988,
S, Self Org
1988,
Neural Ass Memory,
Complex
Comput, P219 V,
Systems,
V7, 1988
1995
1988 3.3453
3.4191
3.3453 1995
1996
1995 1996
2000
1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P
Kohonen
P321 T, 1988,
Broomhead
V2, D S, 1988,Self Org Ass Memory,
Complex Systems,V, 1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
Kohonen T, 1988,V2,
P P321
Kohonen
Broomhead
Self Org T, D 1988,
S,
Ass Self
1988, Org Ass Memory,
Complex
Memory, Systems, V, 1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
P
Broomhead
V2, P321
Kohonen D S,
T, 1988, 1988, Complex
Self Org Systems,
Ass Memory, V,
1988 1988
1988 3.345319951995
3.3453
3.34533.3453 1995 1996
1996
1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V, P P P321
V2,
Broomhead D S, 1988, Complex Systems, 1988 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V2, P321
Broomhead
P D S, 1988, Complex Systems, 1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V2, P321
Broomhead D S, 1988, Complex Systems, 1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Broomhead D V2, P321 Complex
Broomhead
S, 1988,
Publications D S, 1988,Systems,
Complex
PEERSystems, 1988 3.3453 1995 1996 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
V2, P321 2018, 6, x FOR REVIEW
1988 1988
3.34533.3453 19951995 1996
1996 ▂▂▂▂▂▂▂▂ 18 of 21
V2, P321 V2, P321 ▂▂▂▂▂▂▂▂
▂▂▂▃▃▂▂▂▂▂▂▂▂▂▂▂▂▂▂
Hornik
Hornik K, 1990, K, 1990,
Neural Neural Networks,
Networks, V3, P551 V3, P551
1990 1990
3.34533.3453 19951995 1996
1996
▂▂▂▂▂▂▂▂
The top rank is taken by hertz [52] with the highest burst strength of 15.3824. The reference is a
The topbook
ranktitled
is taken by hertzto[52]
“Introduction the with
theorythe highest
of neural burst strength
computation” of 15.3824.
published The 1991.
in the year reference is a
The second
book titled “Introduction to the the
article [53] proposed theory of neural
concept computation”
of multilayer published
feed forward in the
networks as year 1991.approximators.
universal The second
article [53] proposed
The articlesthe concept
with of multilayer
the longest citation burstfeed forward
is starting networks
in 1996 as universal
after two approximators.
years if its publication in 1994
and ends in the year. The book is titled “Neural Networks: A Comprehensive
The articles with the longest citation burst is starting in 1996 after two years if its publication in 1994 Foundation” and
introduces the concept of neural networks from an engineering perspective.
and ends in the year. The book is titled “Neural Networks: A Comprehensive Foundation” and
introduces the concept of neural networks from an engineering perspective.
6. Conclusions
6. Conclusions This paper presents an overall insight and the hidden structure of the journal of neurocomputing
(NC) through an extensive bibliometric study on the publications and citations history from 1992–
This paper presents an overall insight and the hidden structure of the journal of neurocomputing
2018. Over these years of its publications, NC has emerged as one of the most prominent journals.
(NC) through an extensive bibliometric study on the publications and citations history from 1992–2018.
Table 9 shows the comparison of NC with respect to the several other related journals with respect
Over these years
to the of
TP,its
TC,publications,
CPP, and IF. The NC analysis
has emerged as oneover
is performed of the
lastmost prominent
10 years journals.
of publications. NCTable
stands9 at
shows the comparison of NC with respect to the several other related journals with
the top in terms of the total number of publications with TP of 7954 and ranks at the 2nd spot in terms respect to the TP,
TC, CPP, and of IF. Thecitations.
total analysisWith is performed
respect to over the IF, last
NC10(3.317)
years of publications.
ranks above the Soft NC computing
stands at the top in
(2.472) and
terms of theEngineering
total number of publications
Applications withIntelligence
of Artificial TP of 7954(2.894).
and ranks at the 2nd spot in terms of total
citations. With respect to the IF, NC (3.317) ranks above the Soft computing (2.472) and Engineering
Table 9. Comparison of NC with other related Journals.
Applications of Artificial Intelligence (2.894).
Journal
In this paper, we have explored the publication history Induction Year bibliometric
using TP (10 Years) TC (10 Years) and
methods CPPtechniques.
Impact Factor
Information Sciences (INS) 1968 5125 102,308 20.0 4.832
It probed the publicationSoft structure
Computing and(SC) the citation history 1997 of the journal.
1620 A 14,096
total of 10,308
8.7 papers
2.472
Knowledge-Based Systems (KBS) 1987 2092 31,516 15.1 4.529
were analyzed from 1992–2018, which received a total
Engineering Applications of Artificial Intelligence (EAAI)
of 106,536
1988
citations
1617
(CPP = 10.33).
22,107
The
13.7
highest
2.894
publications came inTransactions
IEEE 2016, while the
on Fuzzy maximum
Systems (IEEE TFS) citations1993were received 1186 in 2015. There are
42,013 35.4 16 papers
7.651
Applied Soft Computing (ASOC) 2001 3581 56,584 15.8 3.541
which got more than 200Neurocomputing
citations and (NC) the most cited paper 1989 came in 2006, which
7954 63,491 got 2762
7.98 citations
3.317
In this paper, we have explored the publication history using bibliometric methods and
techniques. It probed the publication structure and the citation history of the journal. A total of 10,308
papers were analyzed from 1992–2018, which received a total of 106,536 citations (CPP = 10.33). The
highest publications came in 2016, while the maximum citations were received in 2015. There are 16
papers which got more than 200 citations and the most cited paper came in 2006, which got 2762
to date. The most productive and influential author of NC is Cao. China and USA are the top two
nations in publications of NC. Chinese Academy of Sciences, China published the highest number of
papers. Interestingly, from the overall compilation of the bibliometric results, it is evident that China
has played a prominent role in the publications and citations structure of the NC.
Table 9. Comparison of NC with other related Journals.
Journal Induction Year TP (10 Years) TC (10 Years) CPP Impact Factor
Information Sciences (INS) 1968 5125 102,308 20.0 4.832
Soft Computing (SC) 1997 1620 14,096 8.7 2.472
Knowledge-Based Systems (KBS) 1987 2092 31,516 15.1 4.529
Engineering Applications of
1988 1617 22,107 13.7 2.894
Artificial Intelligence (EAAI)
IEEE Transactions on Fuzzy
1993 1186 42,013 35.4 7.651
Systems (IEEE TFS)
Applied Soft Computing (ASOC) 2001 3581 56,584 15.8 3.541
Neurocomputing (NC) 1989 7954 63,491 7.98 3.317
However, one thing to be noted is that there may be certain limitations in the study because of
the focus being on the data retrieved from the WoS database. The limitations include the coverage of
research publications wherein WoS omits certain research articles, a smaller database of journals which
leads to under-reported statistics, and so on. However, the data quality in WoS is tremendous and is
thus the most acknowledged source of almost all scientometric studies. Therefore, the major aim of
this paper is to reveal the current status of the NC publications by utilizing the results in WoS [54,55].
The other limitation of this study arises from the fact that it is from the metric level, that is, it deals
with the number of citations and papers. However, numbers do represent quantity but citations do not
represent the quality. Another limitation is that this study creates a profile of the NC journal rather
than the area itself, although it can be claimed that NC has been the pioneer in leading the research in
this field. Certain limitations arise due to data retrieved from WoS as not all journals are indexed with
WoS and thus an array of citations are missed. A comparison with other indexing platforms such as
Scopus, Google Scholar can be a good future scope of this study.
In conclusion, the journal of NC has played an important role in shaping academic research since
its inception. NC is certainly discovering and developing trends in the domain of soft computing.
Author Contributions: Conceptualization: P.K.M.; Methodology: A.K.S., Data Curation, M.J.; Writing—Original
Draft Preparation: M.J.; Writing—Review & Editing: M.J., A.K.S., P.K.M. and A.A.; Supervision: P.K.M. and A.A.
Funding: This research received no external funding.
Acknowledgments: The authors gratefully acknowledge the valuable comments received from the editors and
the reviewers, which has helped them in improving the paper significantly.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Garcia-Silvente, Y.A.M. An overview of iris recognition: A bibliometric analysis. Scientometrics 2014,
101, 2003–2033.
2. Merigó, J.M.; Rocafort, A.; Aznar-Alarcón, J.P. Bibliometric Overview of Business & Economics Research.
J. Bus. Econ. Manag. 2016, 17, 397–413.
3. Du, Y. A Bibliometrics Portrait of Chinese Research through the Lens of China Economic Review. A research
proposal. Econ. Manag. Res. Proj. 2012, 1, 79–91.
4. Hoepner, A.G.F.; Kant, B.; Scholtens, B.; Yu, P.S. Environmental and ecological economics in the 21st century:
An age adjusted citation analysis of the influential articles, journals, authors and institutions. Ecol. Econ.
2012, 77, 193–206. [CrossRef]
5. Kolle, S.R.; Vijayashree, M.S.; Shankarappa, T.H. Highly cited articles in malaria research: A bibliometric
analysis. Collect. Build. 2017, 36, 45–57. [CrossRef]
6. Jiang, H.; Qiang, M.; Lin, P. A topic modeling based bibliometric exploration of hydropower research.
Renew. Sustain. Energy Rev. 2016, 57, 226–237. [CrossRef]
7. Yataganbaba, A.; Kurtbaş, I. A scientific approach with bibliometric analysis related to brick and tile drying:
A review. Renew. Sustain. Energy Rev. 2016, 59, 206–224. [CrossRef]
8. Lee, C.I.S.G.; Felps, W.; Baruch, Y. Toward a taxonomy of career studies through bibliometric visualization.
J. Vocat. Behav. 2014, 85, 339–351. [CrossRef]
9. El Khaled, D.; Novas, N.; Gazquez, J.A.; Manzano-Agugliaro, F. Dielectric and bioimpedance research
studies: A Scientometric approach using the scopus database. Publications 2018, 6, 6. [CrossRef]
10. Aaen-Stockdale, C. Selfish Memes: An Update of Richard Dawkins’ Bibliometric Analysis of Key Papers in
Sociobiology. Publications 2017, 5, 12. [CrossRef]
11. Vanleeuwen, T. Letter to the editor Publication trends in social psychology journals: A long-term bibliometric
analysis. Eur. J. Soc. Psychol. 2013, 11, 9–11. [CrossRef]
12. Arnott, D.; Pervan, G. A critical analysis of decision support systems research. Formul. Res. Methods Inf. Syst.
2015, 20, 127–168.
13. Arnott, D.; Pervan, G. A Critical Analysis of Decision Support Systems Research Revisited: The Rise of
Design Science. In Enacting Research Methods in Information Systems; Palgrave Macmillan: Cham, Switzerland,
2016; Volume 29, pp. 43–103.
14. Kim, M.C.; Jeong, Y.K.; Song, M. Investigating the integrated landscape of the intellectual topology of
bioinformatics. Scientometrics 2014, 101, 309–335. [CrossRef]
15. Song, M.; Kim, S.; Zhang, G.; Ding, Y.; Chambers, T. Productivity and influence in bioinformatics:
A biliographic analysis using PubMed central. J. Am. Soc. Inf. Sci. Technol. 2014, 65, 352–371. [CrossRef]
16. Loock, M.; Hinnen, G. Heuristics in organizations: A review and a research agenda. J. Bus. Res. 2015,
68, 2027–2036. [CrossRef]
17. Huang, Y.; Schuehle, J.; Porter, A.L.; Youtie, J. A systematic method to create search strategies for emerging
technologies based on the Web of Science: Illustrated for ‘Big Data’. Scientometrics 2015, 105, 2005–2022.
[CrossRef]
18. Prathap, G. Big data and false discovery: Analyses of bibliometric indicators from large data sets.
Scientometrics 2014, 98, 1421–1422. [CrossRef]
19. Garousi, V. A bibliometric analysis of the Turkish software engineering research community. Scientometrics
2015, 105, 23–49. [CrossRef]
20. Blanco-Mesa, F.; Merigó, J.M.; Gil-Lafuente, A.M. Fuzzy decision making: A bibliometric-based review.
J. Intell. Fuzzy Syst. 2017, 32, 2033–2050. [CrossRef]
21. Yu, D.; Xu, Z.; Wang, W. Bibliometric analysis of fuzzy theory research in China: A 30-year perspective.
Knowl.-Based Syst. 2018, 141, 188–199. [CrossRef]
22. Shukla, A.K.; Sharma, R.; Muhuri, P.K. A Review of the Scopes and Challenges of the Modern Real-Time
Operating Systems. Int. J. Embed. Real-Time Commun. Syst. 2018, 9, 66–82. [CrossRef]
23. Yu, D.; Li, D.F.; Merigó, J.M.; Fang, L. Mapping development of linguistic decision making studies. J. Intell.
Fuzzy Syst. 2016, 30, 2727–2736. [CrossRef]
24. Emrouznejad, M.M.A. Ordered weighted averaging operators 1988–2014: A citation based literature survey.
Int. J. Intell. Syst. 2014, 29, 994–1014. [CrossRef]
25. Yu, D.; Shi, S. Researching the development of Atanassov intuitionistic fuzzy set: Using a citation network
analysis. Appl. Soft Comput. 2015, 32, 189–198. [CrossRef]
26. Cobo, M.J.; Martínez, M.A.; Gutiérrez-Salcedo, M.; Fujita, H.; Herrera-Viedma, E. 25years at
Knowledge-Based Systems: A bibliometric analysis. Knowl.-Based Syst. 2015, 80, 3–13. [CrossRef]
27. Merigó, J.M.; Blanco-Mesa, F.; Gil-Lafuente, A.M.; Yager, R.R. Thirty years of the International Journal of
Intelligent Systems: A bibliometric review. Int. J. Intell. Syst. 2017, 32, 526–554. [CrossRef]
28. Xu, Z.; Yu, D.; Kao, Y.; Lin, C.T. The structure and citation landscape of IEEE Transactions on Fuzzy Systems
(1994–2015). IEEE Trans. Fuzzy Syst. 2018, 26, 430–442.
29. Laengle, S.; Merigó, J.M.; Miranda, J.; Słowiński, R.; Bomze, I.; Borgonovo, E.; Dyson, R.G.; Oliveira, J.F.;
Teunter, R. Forty years of the European Journal of Operational Research: A bibliometric overview. Eur. J.
Oper. Res. 2017, 262, 803–816. [CrossRef]
30. Cancino, C.; Merigó, J.M.; Coronado, F.; Dessouky, Y.; Dessouky, M. Forty years of Computers & Industrial
Engineering: A bibliometric analysis. Comput. Ind. Eng. 2017, 113, 614–629.
31. Yu, D.; Xu, Z.; Pedrycz, W.; Wang, W. Information Sciences 1968–2016: A retrospective analysis with text
mining and bibliometric. Inf. Sci. 2017, 418–419, 619–634. [CrossRef]
32. Merigó, J.M.; Pedrycz, W.; Weber, R.; De la Sotta, C. Fifty years of Information Sciences: A bibliometric
overview. Inf. Sci. 2018, 432, 245–268. [CrossRef]
33. Wakeling, S.; Willett, P.; Creaser, C.; Fry, J.; Pinfield, S.; Spezi, V. Transitioning from a Conventional to a
‘Mega’ Journal: A Bibliometric Case Study of the Journal Medicine. Publications 2017, 5, 7. [CrossRef]
34. Muhuri, P.K.; Shukla, A.K.; Janmaijaya, M.; Basu, A. Applied Soft Computing: A Bibliometric Analysis of
the Publications and Citations during (2004–2016). Appl. Soft Comput. 2018, 69, 381–392. [CrossRef]
35. Amiguet, L.; Gil-Lafuente, A.M.; Kydland, F.E.; Merigó, J.M. One hundred and twenty-five years of the
Journal of Political Economy: A bibliometric overview. J. Political Econ. 2017, 125, 6.
36. Martínez-López, F.J.; Merigó, J.M.; Valenzuela, L.; Nicolás, C. Fifty years of the European Journal of
Marketing: A bibliometric analysis. Eur. J. Mark. 2018, 52, 439–468. [CrossRef]
37. Wang, W.; Laengle, S.; Merigó, J.M.; Yu, D.J.; Herrera-Viedma, E.; Cobo, M.J.; Bouchon-Meunier, B.
A bibliometric analysis of the first twenty-five years of the International Journal of Uncertainty, Fuzziness
and Knowledge-Based Systems. Int. J. Uncertain. Fuzziness Knowl.-Based Syst. 2018, 26, 169–193. [CrossRef]
38. Tur-Porcar, A.; Mas-Tur, A.; Merigó, J.M.; Roig-Tierno, N.; Watt, J. A bibliometric history of the Journal of
Psychology between 1936 and 2015. J. Psychol. 2018, 152, 199–225. [CrossRef] [PubMed]
39. Neurocomputing. Available online: https://www.journals.elsevier.com/neurocomputi-ng (accessed on
21 February 2018).
40. Hirsch, J.E. An index to quantify an individual’s scientific research output. Proc. Natl. Acad. Sci. USA 2005,
102, 16569–16572. [CrossRef] [PubMed]
41. Chen, C. CiteSpace II: Detecting and visualizing emerging trends and transient patterns in scientific literature.
J. Assoc. Inf. Sci. Technol. 2006, 57, 359–377. [CrossRef]
42. Huang, G.B.; Zhu, Q.Y.; Siew, C.K. Extreme learning machine: Theory and applications. Neurocomputing
2006, 70, 489–501. [CrossRef]
43. Zhang, G.P. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 2003,
50, 159–175. [CrossRef]
44. Suykens, J.A.K.; Brabanter, J.D.; Lukas, L.; Vandewalle, J. Weighted least squares support vector machines:
Robustness and sparse approximation. Neurocomputing 2002, 48, 85–105. [CrossRef]
45. Kim, K. Financial time series forecasting using support vector machines. Neurocomputing 2003, 55, 307–319.
[CrossRef]
46. Kohonen, T. The self-organizing map. Neurocomputing 1998, 21, 1–6. [CrossRef]
47. Mubashir, M.; Shao, L.; Seed, L. A survey on fall detection: Principles and approaches. Neurocomputing 2013,
100, 144–152. [CrossRef]
48. Zong, W.; Huang, G.B.; Chen, Y. Weighted extreme learning machine for imbalance learning. Neurocomputing
2013, 101, 229–242. [CrossRef]
49. Huang, G.B.; Zhou, H.; Ding, X.; Zhang, R. Extreme learning machine for regression and multiclass
classification. IEEE Trans. Syst. Man Cybern. Part. B Cybern. 2012, 42, 513–529. [CrossRef] [PubMed]
50. Chang, C.C.; Lin, C.J. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2011,
3, 27. [CrossRef]
51. Huang, G.B.; Wang, D.H.; Yuan, L. Extreme learning machines: A survey. Int. J. Mach. Learn. Cybern. 2011,
2, 107–122. [CrossRef]
52. John, H.; Krogh, A.; Palmer, R.G. Introduction to the Theory of Neural Computation; Addison-Wesley: Boston,
MA, USA, 1991.
53. Haykin, S. Neural Networks: A Comprehensive Foundation; Macmillan Publishers: New York, NY, USA,
2004; p. 41.
54. Fiala, D.; Tutoky, G. Computer Science Papers in Web of Science: A Bibliometric Analysis. Publications 2017,
5, 23. [CrossRef]
55. Arik, B.T.; Arik, E. “Second Language Writing” Publications in Web of Science: A Bibliometric Analysis.
Publications 2017, 5, 4. [CrossRef]
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Neuro Computing Publications

Transféré par

Informations du document

Copyright

Formats disponibles

Partager ce document

Partager ou intégrer le document

Options de partage

Avez-vous trouvé ce document utile ?

Ce contenu est-il inapproprié ?

Droits d'auteur :

Formats disponibles

Neuro Computing Publications

Transféré par

Droits d'auteur :

Formats disponibles

publications

Keywords: neurocomputing; bibliometric study; scientometric mapping; co-citation analysis; Web

Publications 2018, 6, 32; doi:10.3390/publications6030032 www.mdpi.com/journal/publications

2. Methodology and Performance Indicators

3. Citation Structure of NC Publications

Figure 2. Citations structure of NC over the years.

35 Citations Per Year

Figure 3. Citations per year of the NC computing.

Table 1. General citation Structure in the Journal: NC (1992–2018).

Year ≥200 ≥100 ≥50 ≥20 ≥10 ≥5 ≥1 0 TP h-Index TC CPP

Table 2. Top 40 cited publications in NC.

Rank Title Authors Year TC Citations per Year

Rank Title Authors Year TC Citations per Year

Top Authorship, Country, and Institutions

Table 3. Most Productive and Influential Authors in NC (1992–2018).

Rank Name Country Affiliation TP TC CPP h-Index

Figure 6. Institution Co-Citation Analysis.

Figure 7. Bibliographic coupling of the authors in NC.

Figure 8. Bibliographic coupling of the countries publishing in NC.

Publications 2018, 6, x FOR PEER REVIEW 13 of 21

Figure 9. Bibliographic coupling of the institutions publishing in NC.

5. Document Co-Citation Network

Figure 10. Document co-citation analysis.

Rank Title Year Source Authors

Table 6. Top 10 Highly Cited References in NC.

Rank Title Year Source Authors

5.1. Cluster Detection and Analysis

Figure 11. Document co-citations clusters.

Figure 12. Timeline view of the document co-citations.

Table 7. Top 12 clusters in NC publications.

Table 9. Comparison of NC with other related Journals.

Vous aimerez peut-être aussi