Académique Documents
Professionnel Documents
Culture Documents
Semester 1, 2003
BPNN in Practice
page 1 of 1
Semester 1, 2003
Neural
Networks
trained
with
emulate
the
human
memorys
associative
page 2 of 2
Semester 1, 2003
page 3 of 3
Semester 1, 2003
Oi ( k + 1) = f wij Oi ( k ) , 0 j N 1
i =0
page 4 of 4
Semester 1, 2003
Type of Learning
Supervised Learning
o the input vectors and the corresponding output
vectors are given
o the ANN learns to approximate the function
from the inputs to the outputs
page 5 of 5
Semester 1, 2003
Reinforcement Learning
o the input vectors and a reinforcement signal are
given
o the reinforcement signal tells how good the
true output was
Unsupervised Learning
o only input are given
o the ANN learns to form internal representations
or codes for the input data that can then be
used e.g. for clustering
page 6 of 6
Semester 1, 2003
Hebbian Learning
In 1949, Donald Hebb proposed one of the key ideas
in biological learning, commonly known as Hebbs
Law.
Hebbs Law states that if neuron i is near enough to
excite neuron j and repeatedly participates in its
activation, the synaptic connection between these two
neurons is strengthened and neuron j becomes more
sensitive to stimuli from neuron i.
Hebbs Law can be represented in the form of two
rules:
If two neurons on either side of a connection are
activated synchronously, then the weight of that
connection is increased.
If two neurons on either side of a connection are
activated asynchronously, then the weight of that
connection is decreased.
page 7 of 7
Semester 1, 2003
page 8 of 8
Semester 1, 2003
page 9 of 9
Semester 1, 2003
Step 4: Iteration
Increase iteration p by one, go back to Step 2.
Competitive Learning
Neurons compete among themselves to be activated
While in Hebbian Learning, several output neurons
can be activated simultaneously, in competitive
learning, only a single output neuron is active at any
time.
The output neuron that wins the competition is
called the winner-takes-all neuron.
In the late 1980s, Kohonen introduced a special call
of ANN called self-organising maps. These maps are
based on competitive learning.
Week 3 Lecture Notes
page 10 of 10
Semester 1, 2003
Self-organising Map
Our brain is dominated by the cerebral cortex, a very
complex structure of billions of neurons and hundreds
of billions of synapses.
The cortex includes areas that are responsible for
different human activities (motor, visual, auditory,
etc), and associated with different sensory input.
Each sensory input is mapped into a corresponding
area of the cerebral cortex. The cortex is a selforganising computational map in the human brain.
page 11 of 11
Semester 1, 2003
page 12 of 12
Semester 1, 2003
training
proceeds,
the
neighbourhood
size
gradually decreases.
page 13 of 13
Semester 1, 2003
page 14 of 14
Semester 1, 2003
page 15 of 15
Semester 1, 2003
Step 3: Learning
o Update the synaptic weights
until
minimum-distance
Euclidean
page 16 of 16