ARTIFICIAL NEURAL

NETWORKS: AN
INTRODUCTION

Arsha J K, AP,
Computer Science and Engineering, 1
VJCET, Vazhakulam
 Neural Networks
● Neural network was inspired by the design and functioning of
human brain and components.
Definition:
● Information processing model that is inspired by the way
biological nervous system (i.e) the brain, process information.
● ANN is composed of large number of highly interconnected
processing elements(neurons) working in union to solve
problems.
● It is configured for special application such as pattern
recognition and data classification through a learning process.
● 85-90% accurate.

Arsha J K, AP,
Computer Science and Engineering, 2
VJCET, Vazhakulam
BRAIN COMPUTATION
The human brain contains about 10 billion nerve cells, or
neurons. On average, each neuron is connected to other
neurons through approximately 10,000 synapses.

Arsha J K, AP,
Computer Science and Engineering, 3
VJCET, Vazhakulam
INTERCONNECTIONS IN BRAIN

Arsha J K, AP,
Computer Science and Engineering, 4
VJCET, Vazhakulam
 BIOLOGICAL NEURAL NETWORK

• Human brain consist of a huge number of neurons,

appx 10 ^11 , with numerous interconnections
• Consist of 3 main parts
– Soma/cell body where cell nucleus is located
– Dendrites where nerve is connected to cell body
– Axon which carries the impulse of neuron
Arsha J K, AP,
Computer Science and Engineering, 5
VJCET, Vazhakulam
✔ In the human brain, a typical neuron collects signals
from others through a host of fine structures called
dendrites.
✔ The neuron sends out spikes of electrical activity
through a long, thin stand known as an axon, which
splits into thousands of branches.
✔ At the end of each branch, a structure called a
synapse converts the activity from the axon into
electrical effects that inhibit or excite activity in the
connected neurons.
Arsha J K, AP,
Computer Science and Engineering, 6
VJCET, Vazhakulam
• Electric impulse is passed between synapse and dendrites.
• Synapse- Axon split into strands and strands terminates into small
bulb like organs called as synapse.
• It is a chemical process which results in increase /decrease in the
electric potential inside the body of the receiving cell.
• If the electric potential reaches a threshold value, receiving cell
fires & pulse / action potential of fixed strength and duration is
send out through the axon to synaptic junction of the cell.
• After that, cell has to wait for a period called refractory period.
• Synapses are said to be
– Inhibitory if the parsing impulses prevent the firing of receiving cell
– Excitatory If the parsing impulses cause the firing of cells

Arsha J K, AP,
Computer Science and Engineering, 7
VJCET, Vazhakulam
ASSOCIATION OF BIOLOGICAL NET
WITH ARTIFICIAL NET

Arsha J K, AP,
Computer Science and Engineering, 8
VJCET, Vazhakulam
✔ Figure below shows the mathematical representation of
above discussed chemical reaction taking place in an artificial
neuron

X1
W1
Y
X2 W2
Output
∑ y in
y
Wn

Processing
XN Element

✔ The net input is calculated as

Arsha J K, AP,
9
Computer Science and Engineering,
VJCET, Vazhakulam
• The weight represent the strength of the
synapse connecting input and the output
neuron
• A positive weight corresponds to the
excitatory synapses
• A negative weight corresponds to the
inhibitory synapses

Arsha J K, AP,
Computer Science and Engineering, 10
VJCET, Vazhakulam
ARTIFICIAL NEURAL NET

Information-processing system.

Neurons process the information.

The signals are transmitted by means of connection links.

The links possess an associated weight.

The output signal is obtained by applying activations to the net

input.

Arsha J K, AP,
Computer Science and Engineering, 11
VJCET, Vazhakulam
MOTIVATION FOR NEURAL NET

Scientists are challenged to use machines more effectively for

tasks currently solved by humans.

Symbolic rules don't reflect processes actually used by humans.

Traditional computing excels in many areas, but not in others.

Arsha J K, AP,
Computer Science and Engineering, 12
VJCET, Vazhakulam
The major areas being:

Massive parallelism

Distributed representation and computation

Learning ability

Generalization ability

Adaptivity

Inherent contextual information processing

Fault tolerance

Low energy consumption.

Arsha J K, AP,
Computer Science and Engineering, 13
VJCET, Vazhakulam
 Artificial Neural Network : An
Introduction
⚫ Resembles the characteristic of biological neural network.
⚫ Nodes – interconnected processing elements (units or neurons)
⚫ Neuron is connected to other by a connection link.
⚫ Each connection link is associated with weight which has
information about the input signal.
⚫ ANN processing elements are called as neurons or artificial
neurons , since they have the capability to model networks of
original neurons as found in brain.
⚫ Internal state of neuron is called activation or activity level of
neuron, which is the function of the inputs the neurons
receives.
⚫ Neuron can send only one signal at a time.
Arsha J K, AP,
Computer Science and Engineering, 14
VJCET, Vazhakulam
 Basic Operation of a Neural Net
• X1 and X2 – input neurons.
• Y- output neuron
• Weighted interconnection links- W1 and W2.
• Net input calculation is :
• Output is :
• Output= function (net input calculated)

W1
Y
X1

W2 Arsha J K, AP,
Computer Science and Engineering,
X2 VJCET, Vazhakulam 15
 • The function to be applied over the net input is called
activation function.
• Weight involved in ANN is equal to the slope of linear
straight line (y=mx).

INPUT
X m Y mx

• To obtain y , the slop of m is directly multiplied with

the input signal.
• This is linear equation when the slop and input is
linearly varied
• This shows that the weight involved in ANN is
equivalent to the slop of linear straight line
Arsha J K, AP,
Computer Science and Engineering, 16
VJCET, Vazhakulam
Terminology Relation Between Biological And
Artificial Neuron

Biological Neuron Artificial Neuron

Cell Neuron
Dendrites Weights or interconnections
Soma Net input
Axon Output

Arsha J K, AP,
Computer Science and Engineering, 17
VJCET, Vazhakulam
 Characteristics of ANN:
• Neurally implemented mathematical model
• Large number of processing elements called neurons exists
here.
• Interconnections with weighted linkage hold informative
knowledge.
• Input signals arrive at processing elements through
connections and connecting weights.
• Processing elements can learn, recall and generalize from the
given data.
• Computational power is determined by the collective
behavior of neurons.
– ANN is a connection models, parallel distributed processing models,
self-organizing systems, neuro-computing systems and neuro morphic
system.

Arsha J K, AP,
Computer Science and Engineering, 18
VJCET, Vazhakulam
 Evolution of neural networks
Year Neural Designer Description
network
1943 McCulloch and McCulloch and Arrangement of neurons is combination of logic gate.
Pitts neuron Pitts Unique feature is threshold

1949 Hebb network Hebb If two neurons are active, then their connection
strengths should be increased.
1958,1959, Perceptron Frank Weights are adjusted to reduce the difference between
1962,1988, Adaline Rosenblatt, the net input to the output unit and the desired output
1960 Block, Minsky
and Papert
Widrow and Hoff
1972 Kohonen Kohonen Inputs are clustered to obtain a fired output neuron.
self-organizing
feature map
1982,1984, Hopfield John Hopfield Based on fixed weights.
1985,1986, network and Tank Can act as associative memory nets
1987
1986 Back Rumelhart, i) Multilayered
propagation Hinton and ii) Error propagated backward from output to the
network Williams hidden units
Arsha J K, AP, 19
Computer Science and Engineering,
Year Neural network Designer Description

1988 Counter propagation Grossberg Similar to kohonen network

network

1987-1990 Adaptive resonance Carpenter and Designed for binary and

Theory(ART) Grossberg analog inputs.

1988 Radial basis function Broomhead and Resemble back propagation

network Lowe network , but activation
function used is Gaussian
function

1988 Neo cognitron Fukushima For character recogniton.

Arsha J K, AP,
Computer Science and Engineering, 20
VJCET, Vazhakulam
 Basic models of ann
✔ Models are based on three entities
❖ The model’s synaptic interconnections.
❖ The training or learning rules adopted for
updating and adjusting the connection weights.
❖ Their activation functions

Arsha J K, AP,
Computer Science and Engineering, 21
VJCET, Vazhakulam
 CONNECTION
• The arrangement of neurons to form layers and the
connection pattern formed within and between layers
is called the network architecture.
• Five types:
– Single layer feed forward network
– Multilayer feed-forward network
– Single node with its own feedback
– Single-layer recurrent network
– Multilayer recurrent network
Arsha J K, AP,
Computer Science and Engineering, 22
VJCET, Vazhakulam
 Single layer Feed- Forward Network

• Layer is formed by taking

processing elements and
combining it with other
processing elements.
• Input and output are linked
with each other
• Inputs are connected to the
processing nodes with
various weights, resulting in
series of outputs one per
node.
Arsha J K, AP,
Computer Science and Engineering, 23
VJCET, Vazhakulam
 Multilayer feed-forward network
• Formed by the interconnection of several layers.
• Input layer receives input and buffers input signal.
• Output layer generated output.
• Layer between input and output is called hidden layer.
• Hidden layer is internal to the network.
• Zero to several hidden layers in a network.
• More the hidden layer, more is the complexity of network, but efficient output is
produced.

Arsha J K, AP,
Computer Science and Engineering, 24
VJCET, Vazhakulam
 Feed back network
• If no neuron in the output layer is an input
to a node in the same layer / proceeding
layer – feed forward network.
• If outputs are directed back as input to the
processing elements in the same
layer/proceeding layer –feedback
network.
• If the output are directed back to the input
of the same layer then it is lateral
feedback.
• Recurrent networks are networks with
feedback networks with closed loop.
• Fig 2.8 (A) –simple recurrent neural network
having a single neuron with feedback to itself.
• Fig 2.9 – single layer network with feedback
from output can be directed to processing
element itself or to other processing
element/both.

Arsha J K, AP,
Computer Science and Engineering, 25
VJCET, Vazhakulam
• Maxnet – competitive interconnections
having fixed weights.
• On-center-off-surround/lateral
inhibiton structure – each
processing neuron receives two
different classes of inputs-
“excitatory” input from nearby
processing elements & “ inhibitory”
elements from more distantly located
precessing elements. This type of
interconnection is shown below

Arsha J K, AP,
Computer Science and Engineering, 26
VJCET, Vazhakulam
• Processing element output can be directed back to the nodes
in the preceding layer, forming a multilayer recurrent
network.
• Processing element output can be directed to processing
element itself or to other processing element in the same
layer.

Arsha J K, AP,
Computer Science and Engineering, 27
VJCET, Vazhakulam
 learning
✔ The main property of ANN
✔ NN adapt itself to a stimulus by making proper parameter
adjustments resulting in the production of desired response
✔ Two broad kinds of learning in ANNs is :
✔ parameter learning – updates connecting weights in a neural net.
✔ Structure learning – focus on change in the network which include the
number of processing elements and their connection type
✔ Apart from these, learning in ANN is classified into three categories
as
i) supervised learning
ii) unsupervised learning
Iii) reinforcement learning

Arsha J K, AP,
Computer Science and Engineering, 28
VJCET, Vazhakulam
 Supervised learning
✔ Learning with the help of a teacher.
✔ Example : learning process of a small
child.
✔ Child doesn’t know read/write.
✔ Their each & every action is
supervised by a teacher
✔ In ANN, each input vector requires a
corresponding target vector, which
represents the desired output.
✔ The input vector along with target vector is
called training pair.
✔ The input vector results in output vector.
✔ The actual output vector is compared with
desired output vector.
✔ If there is a difference means an error
signal is generated by the network.
✔ It is used for adjustment of weights until
actual output matches desired output.

Arsha J K, AP,
Computer Science and Engineering, 29
VJCET, Vazhakulam
 Unsupervised learning
✔ Learning is performed without the help of a teacher.
✔ Example: tadpole – learn to swim by itself.
✔ In ANN, during training process, network receives input patterns and organize it to
form clusters.
✔ From the Fig. it is observed that no feedback is applied from environment to
inform what output should be or whether they are correct.
✔ The network itself discover patterns, regularities, features/ categories from the
input data and relations for the input data over the output.
✔ Exact clusters are formed by discovering similarities & dissimilarities so called as
self – organizing.

Arsha J K, AP,
Computer Science and Engineering, 30
VJCET, Vazhakulam
 Reinforcement learning
✔ Similar to supervised learning.
✔ Learning based on critic information is called reinforcement learning & the
feedback sent is called reinforcement signal.
✔ The network receives some feedback from the environment.
✔ Feedback is only evaluative.
✔ The external reinforcement signals are processed in the critic signal
generator, and the obtained critic signals are sent to the ANN for adjustment
of weights properly to get critic feedback in future.

Arsha J K, AP,
Computer Science and Engineering, 31
VJCET, Vazhakulam
 Activation functions
✔ To make work more efficient and for exact output, some force or
activation is given.
✔ Like that, activation function is applied over the net input to calculate
the output of an ANN.
✔ Information processing of processing element has two major parts:
input and output.
✔ An integration function (f) is associated with input of processing
element.
✔ The nonlinear activation function is used to ensure that a neuron’s
response is bounded
✔ When a signal is fed through a multilayer network with a linear
activation functions the output obtained remains the same as that could
be obtained using a single layer network
✔ Due to this reason , nonlinear functions are widely used in multilayer
network compared to linear function
Arsha J K, AP,
Computer Science and Engineering, 32
VJCET, Vazhakulam
✔ Several activation functions are there.
1. Identity function:
it is a linear function which is defined as
f(x) =x for all x
The output is same as the input.
2. Binary step function
it is defined as

where θ represents thresh hold value.

It is used in single layer nets to convert the net input to an
output that is binary. ( 0 or 1)

Arsha J K, AP,
Computer Science and Engineering, 33
VJCET, Vazhakulam
3. Bipolar step function:
It is defined as

where θ represents threshold value

used in single layer nets to convert the net input to an output that is bipolar (+1 or -1).
4. Sigmoid function
used in Back propagation nets.
Two types:
a) binary sigmoid function
-logistic sigmoid function or unipolar sigmoid function.
-it is defined as

where λ – steepness parameter.

-The derivative of this function is
f’(x) = λ f(x)[1-f(x)].
The range of sigmoid function is 0 to 1.

Arsha J K, AP,
Computer Science and Engineering, 34
VJCET, Vazhakulam
b) Bipolar sigmoid function

where λ- steepness parameter and the sigmoid range is between -1 and +1.
- The derivative of this function can be
[1+f(x)][1-f(x)]
- It is closely related to hyperbolic tangent function, which is written as

The derivative of the hyperbolic tangent function is

h’(x)= [1+h(x))][1-h(x)]
Arsha J K, AP,
Computer Science and Engineering, 35
VJCET, Vazhakulam
5. Ramp function

The graphical representation of all these function is

given in the upcoming Figure

Arsha J K, AP,
Computer Science and Engineering, 36
VJCET, Vazhakulam
37
 Important terminologies
• Weight
– The weight contain information about the input signal.
– It is used by the net to solve the problem.
– It is represented in terms of matrix & called as connection
matrix.
– If weight matrix W contains all the elements of an ANN,
then the set of all W matrices will determine the set of all
possible information processing configuration.
– The ANN can be realized by finding an appropriate matrix
W.
– Weight encode long-term memory (LTM) and the
activation states of network encode short-term memory
(STM) in a neural network.
Arsha J K, AP,
Computer Science and Engineering, 38
VJCET, Vazhakulam
 Weight matrix
W=

Arsha J K, AP,
Computer Science and Engineering, 39
VJCET, Vazhakulam
 Weights contd…
• wij –is the weight from processing element ”i” (source node) to
processing element “j” (destination node)

1
X1 bj

w1j

Xi Yj
wij

Xn wnj
Arsha J K, AP,
Computer Science and Engineering, 40
VJCET, Vazhakulam
Bias
– Bias has an impact in calculating net input.
– Bias is included by adding x0 to the input vector x.
– The net output is calculated by

– The bias is of two types

– Positive bias
» Increase the net input
– Negative bias
» Decrease the net input
Arsha J K, AP,
Computer Science and Engineering, 41
VJCET, Vazhakulam
Threshold
– It is a set value based upon which the final output
is calculated.
– Calculated net input and threshold is compared to
get the network output.
– The activation function of threshold is defined as

• where θ is the fixed threshold value

Arsha J K, AP,
Computer Science and Engineering, 42
VJCET, Vazhakulam
• Learning rate
– Denoted by α.
– Control the amount of weight adjustment at each step of
training.
– The learning rate range from 0 to 1.
– Determine the rate of learning at each step
• Momentum Factor
– Convergence is made faster if a momentum factor is added
to the weight updation process.
– Done in back propagation network.
• Vigilance parameter
– Denoted by ρ.
– Used in Adaptive Resonance Theory (ART) network.
– Used to control the degree of similarity.
– Ranges from 0.7 to 1 to perform useful work in controlling
the number of clusters.

Arsha J K, AP,
Computer Science and Engineering, 43
VJCET, Vazhakulam
 Mcculloch-pitts neuron
• Discovered in 1943.
• Usually called as M-P neuron.
• M-P neurons are connected by directed weighted
paths.
• Activation of M-P neurons is binary (i.e) at any time
step the neuron may fire or may not fire.
• Weights associated with communication links may
be excitatory(wgts are positive)/inhibitory(wgts are
negative).
• Threshold plays major role here. There is a fixed
threshold for each neuron and if the net input to the
neuron is greater than the threshold then the neuron
fires.
• They are widely used in logic functions.

Arsha J K, AP,
Computer Science and Engineering, 44
VJCET, Vazhakulam
• A simple M-P neuron is shown in the figure.
• It is excitatory with weight (w>0) / inhibitory with weight –p
(p<0).
• In the Fig., inputs from x1 to xn possess excitatory weighted
connection and Xn+1 to xn+m has inhibitory weighted
interconnections.
• Since the firing of neuron is based on threshold, activation
function is defined as

Arsha J K, AP,
Computer Science and Engineering, 45
VJCET, Vazhakulam
 • For inhibition to be absolute, the threshold with
the activation function should satisfy the
following condition:
θ >nw –p
• Output will fire if it receives “k” or more
excitatory inputs but no inhibitory inputs where
kw≥θ>(k-1) w
✔ The M-P neuron has no particular training
algorithm.
✔ An analysis is performed to determine the
weights and the threshold.
✔ It is used as a building block where any function
or phenomenon is modeled based on a logic
function.
Arsha J K, AP,
Computer Science and Engineering, 46
VJCET, Vazhakulam
 Problems
Implement following using MP Neuron
• Logical AND

• Logical ANDNOT

• XOR

47
 Linear Separability
Consider example with two inputs, x1, x2:
x2
+ +
+ Can view trained network
+ as defining a “separation line”.
+ +
+
What is its equation?

x1

Percepton used for classification

Linear Separability

x2
+ +
OR

− + x1
Linear Separability
x2

− +

AND
− − x1
Linear Separability
x2

+ −
XOR

− + x1
 Linear Separability
x2
Not linearly separable
+ −
XOR

− + x1

Minsky & Papert (1969)

Bad News: Perceptrons can only represent linearly separable functions.
 Linear separability
✔ It is a concept wherein the separation of the input space into
regions is based on whether the network response is positive
or negative.
✔ A decision line is drawn to separate positive or negative
response.
✔ The decision line is also called as decision-making line or
decision-support line or linear-separable line.
✔ The net input calculation to the output unit is given as

✔ The region which is called as decision boundary is

determined by the relation

Computer Science and Engineering, 53

VJCET, Vazhakulam
✔ Consider a network having positive response in the first quadrant and negative
response in all other quadrants with either binary or bipolar data.
✔ Decision line is drawn separating two regions as shown in Fig.
✔ Using bipolar data representation, missing data can be distinguished from mistaken
data. Hence bipolar data is better than binary data.
✔ Missing values are represented by 0 and mistakes by reversing the input values from
+1 to -1 or vice versa.

Computer Science and Engineering, 54

VJCET, Vazhakulam
 Hebb network
• Donald Hebb stated in 1949 that “ In brain, the learning is
performed by the change in the synaptic gap”.
• When an axon of cell A is near enough to excite cell B, and
repeatedly or permanently takes place in firing it, some growth
process or metabolic change takes place in one or both the cells such
than A’s efficiency, as one of the cells firing B, is increased.
• According to Hebb rule, the weight vector is found to increase
proportionately to the product of the input and the learning signal.
• In Hebb learning, two interconnected neurons are ‘on’
simultaneously.
• The weight update in Hebb rule is given by
» Wi(new) = wi (old)+ xi y.
• It is suited more for bipolar data.
• If binary data is used, the weight updation formula cannot
distinguish two conditions namely
– A training pair in which an input unit is “on” and the target value is
“off”
– A training pair in which both the input unit and the target value is “off”.
Computer Science and Engineering,
55
VJCET, Vazhakulam
Flowchart of training
algorithm

Arsha J K, AP,
Computer Science and Engineering, 56
VJCET, Vazhakulam
57
• Steps:
– 0: First initialize the weights.
– 1: Steps 2-4 have to be performed for each input training vector
and target output pair, s:t
– 2: Input activations are set. The activation function for input
layer is identity function.
– Xi =Si for i=1 to n
– 3: Output activations are set.
– 4: Weight adjustment and bias adjustments are performed.
• Wi(new) = wi(old)+xiy
• b(new)=b(old)+y
✔ In step 4, the weight updating formula can be written in vector form as
✔ w(new)=w(old)+y.
✔ Change in weight is expressed as
✔ Δw=xy
✔ Hence,
✔ w(new)=w(old)+Δw
✔ Hebb rule is used for pattern association, pattern categorization,
pattern classification and over a range of other areas
58
 Problems
Implement following using Hebb rule
• Logical AND

• Logical OR

• XOR

Arsha J K, AP,
Computer Science and Engineering, 59
VJCET, Vazhakulam
 TUTORIAL QUESTIONS

1. Describe the necessity of Activation function? Examine the various

aspects of sigmoidal activation function. List the drawbacks.
Calculate the net output of the following neural network using the
bipolar and binary sigmoidal activation function.

Arsha J K, AP,
Computer Science and Engineering, 60
VJCET, Vazhakulam
● A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the
constant of proportionality being equal to 2. The inputs are 4, 10, 5 and 20
respectively. Predict the output?
● Construct a feed forward network with 5 inputs, three hidden nodes and four output
nodes.
● Design an MP neuron using s(a1,a2,a3)=a1a2a3 using bipolar input and targets
● Implement NAND Gate using MP neuron
● Implement NOR gate using MP neuron
● Show that the derivative of Unipolar sigmoid function is
a. f’(x) =λ f(x) [1-f(x)]
● Show that the derivative of bipolar sigmoid function is
a. f’(x) = λ /2 [1+f(x)][1-f(x)]
● Design a Hebb net to implement AND function
● Design a Hebb net to implement OR function
● Design a Hebb net to implement XOR function
● Design a Hebb net to implement And function using
a. Binary input and target value
b. Binary input and bipolar target value
● Implement NOR function using Hebb net by using
a. Bipolar input and target
Arsha J K, AP,
b. Bipolar input and Binary target Computer Science and Engineering,
VJCET, Vazhakulam 61
• Construct a feed forward network
with five input nodes, three hidden
nodes and four output nodes

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
• Construct a feed forward network with
five input nodes, three hidden nodes
and four output nodes that has lateral
inhibition structure in the output layer

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
• Construct a recurrent network with 4
input nodes, three hidden nodes and
2 output nodes that has a feedback
link from hidden layer to input layer

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
 + + +
Using Hebb rule, Find the weight required to
perform the following classification of the given +
input patterns shown below
The pattern is shown as 3X3 matrix form in the + + +
squares. The “+” symbol represents the value 1 “I”
and empty square indicate -1.
Consider “I” belongs to the member of the class so
the target value is 1 and “O” does not belongs + + +
to the member of the class so the target value is
-1 + +
+ + +
“O”

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
 + . .
Using Hebb rule, Find the weight required to
perform the following classification of the + . .
given input patterns shown below
The pattern is shown as 3X3 matrix form in + + +
the squares. The “+” symbol represents “L”
the value 1 and dot indicate -1.
Consider “L” belongs to the member of the
class so the target value is 1 and “U” + . +
does not belongs to the member of the
class so the target value is -1 + . +
+ + +
“U”

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
 + + +
Using Hebb rule, Find the weight required to + . +
perform the following classification of the + + +
given input patterns shown below
The pattern is shown as 3X3 matrix form in + . +
the squares. The “+” symbol represents + . +
the value 1 and dot indicate -1. “A”
Consider “A” belongs to the member of the
class so the target value is 1 and “E” does + + +
not belongs to the member of the class
so the target value is -1 + . .
+ + +
+ . .
+ + +
Arsha J K, AP,
Computer Science and Engineering, “E”
VJCET, Vazhakulam
Using Hebb rule find weights required to
perform following classifications. The
vectors(1 -1 1 -1 ) and (1 1 1 -1) belongs to
class (target value +1); vectors (-1 -1 1 1) and(1
1 -1 -1) do not belongs to class( target value
-1). Also using each of training x vectors as
input, test the response of the net

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam
Distinguish between pattern “X” and pattern “O”

# # # # #
# # # #
# # #
# # # #
# # # # #

Arsha J K, AP,
Computer Science and Engineering,
VJCET, Vazhakulam