Supervised Learning Network
Dr. K. Ganesan
Director, TIFAC-CORE in
Automotive Infotronics
VIT University, Vellore – 632 014
[email protected]

Perceptron Network
•
Perceptron networks come under single-layer feed-forward
networks and also called simple perceptrons. The key
concepts to be considered here are:
•
The perceptron network consists of 3 units namely sensory
unit (input unit), associator unit (hidden unit) and response
unit (output unit)..
•
The sensory units are connected to associator units with fixed
weights having values 1,0 or -1, which are assigned at
random.
•
The binary activation function is used in sensory unit and
associator unit.
•
The response unit has an activation of 1, 0 or -1.
The binary
step with fixed threshold θ is used as activation for associator.
The output signals that are sent from the associator unit to
the response unit are only binary.

A perceptron network with its 3
units is shown in Figure below.

Perceptron Learning Rule
•
In the case of perceptron learning rule, the learning signal is the
difference between the desired and actual response of a neuron.
•
Consider a finite “n” number of input training vectors, with their
associated target (desired) values x(n) and t(n), where “n”
ranges from 1 to N.
•
The target is either +1 or -1.
The output “y” is obtained on the
basis of the net input calculated and activation function being
applied over the net input.
•
y = f(yin) = 1 if yn > θ
•
= 0 if – θ ≤ yin ≤ θ
•
= -1 if yin < - θ
•
The weight updation in case of perceptron learning is an as
shown:
•
If y ≠ t, then
•
w(new) = w(old) + α.tx
•
else, we have
•
w(new) = w(old).

Perceptron Learning Rule
•
In the original perceptron network, the output
obtained from the associator unit is a binary
vector, and hence that output can be taken as
input signal to the response unit, and
classification can be performed.
•
Here only the weights between the associator
unit and the output unit can be adjusted, and
weights between the sensory and associator
units are fixed.
•
As a result the discussion of the network is
limited to a single portion.
•
Thus the associator unit behaves like the input
unit.

Perceptron training algorithm for
single output classes
•
The perceptron algorithm can be used for
either binary or
bipolar input vectors, having bipolar targets
, threshold
being fixed and variable bias.
•
This algorithm is
not sensitive to the initial values of the
weights or the value of the learning rate
.
•
In the algorithm discussed below, initially the inputs are
assigned.
•
Then the net input is calculated.
The output of the network
is obtained by applying the activation function over the
calculated net input.
•
On performing the comparison over the calculated and the
desired output, the weight updation process is carried out.
•
The entire network is trained based on the mentioned
stopping criterion.