Académique Documents
Professionnel Documents
Culture Documents
Neural Networks
Danny Leung
CS157B, Spring 2006
Professor Sin-Min Lee
Artificial Intelligence
for Data Mining
Neural networks are useful for data mining and
decision-support applications.
2
Neural Network
Characteristics
Number of
inputs/outputs is variable
4
Biological Background
A neuron: many-inputs / one-output unit
5
Basics of a Node
A node is an
element which
performs a
function
y = fH((wixi) +
Connection
Wb)
Node
6
A Simple Preceptron
Binary logic
application
fH(x) [linear
threshold]
Wi = random(-1,1)
Y = u(W0X0 + W1X1
+ Wb)
7
Preceptron Training
Its a single-unit network
Wi = * (D-Y).Ii
= Learning Rate
D = Desired Output
8
Neural Network
Learning
From experience: examples / training
data
Evaluate output
Adapt weights
11
Topologies Back-
Propogated Networks
Inputs are put
through a
Hidden Layer
before the output
layer
All nodes
connected
between layers
12
BP Network
Supervised Training
Desired output of the training examples
Improved performance
13
Neural Network
Topology
Characteristics
Set of inputs
Set of outputs
15
Overview
Advantages
Adapt to unknown situations
Robustness: fault tolerance due to network
redundancy
Autonomous learning and generalization
Disadvantages
Not exact
Large complexity of the network structure
16
Referenced Work
Intro to Neural Networks - Computer Vision Applications and Training
Techniques. Doug Gray. www.soe.ucsc.edu/~taoswap/
GroupMeeting/NN_Doug_2004_12_1.ppt
17