TABLE OF CONTENTS

S. No. Experiment Date Remarks

1 Write a Program to implement Perceptron.

2 Write a Program to implement AND OR Gates

using Perceptron.

Objective: Write a Program to implement full

3 counter propagation network.

Write a MATLAB Script containing four

4
functions Addition, Subtraction,Multiplication

and Division

8
 Experiment-1

Objective: Write a Program to implement Perceptron.

Code:
clear;
clc;
x=[1 1 -1 -1;1 -1 1 -1];
t=[1 -1 -1 -1];
w=[0 0];
b=0;
alpha=input('enter learning rate=');
theta=input('enter threshold value=');
con=1;
epoch=0;
while con
con=0;
for i=1:4
yin = b+x(1,i)*w(1)+x(2,i)*w(2);
if yin>theta
y=1;
end
if yin<=theta & yin>=-theta
y=0;
end
if yin<-theta
y=-1;
end
if y-t(i)
con=1;
for j=1:2
 w(j)=w(j)+alpha*t(i)*x(j,i);
end
b=b+alpha*t(i);
end
end
epoch=epoch+1;
end
disp('Perceptron For AND function');
disp('Final weight matrix');
disp(w);
disp('Final Bias');
disp(b);
OUTPUT:
 Experiment-2

Write a Program to implement AND & OR Gates using Perceptron.

Code (AND ):

import numpy as np
class Perceptron:
def __init__(self, num_inputs, learning_rate=0.01, epochs=100):
self.learning_rate = learning_rate
self.epochs = epochs
self.weights = np.zeros(num_inputs + 1) # +1 for the bias
self.errors = []

def predict(self, inputs):

summation = np.dot(inputs, self.weights[1:]) + self.weights[0]
return 1 if summation > 0 else 0

def train(self, training_data, labels):

for _ in range(self.epochs):
total_error = 0
for inputs, label in zip(training_data, labels):
prediction = self.predict(inputs)
error = label - prediction
total_error += error
self.weights[1:] += self.learning_rate * error * inputs
self.weights[0] += self.learning_rate * error
self.errors.append(total_error)

if __name__ == "__main__":
# Example usage:
training_data = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
labels = np.array([0, 0, 0, 1])

perceptron = Perceptron(num_inputs=2, learning_rate=0.1, epochs=100)

perceptron.train(training_data, labels)

test_inputs = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])

for inputs in test_inputs:
prediction = perceptron.predict(inputs)
print(f"Input: {inputs}, Prediction: {prediction}")
OUTPUT:
Code (OR ):
import numpy as np

class Perceptron:
def __init__(self, num_inputs, learning_rate=0.01, epochs=100):
self.learning_rate = learning_rate
self.epochs = epochs
self.weights = np.zeros(num_inputs + 1) # +1 for the bias
self.errors = []

def predict(self, inputs):

summation = np.dot(inputs, self.weights[1:]) + self.weights[0]
return 1 if summation > 0 else 0

def train(self, training_data, labels):

for _ in range(self.epochs):
total_error = 0
for inputs, label in zip(training_data, labels):
prediction = self.predict(inputs)
error = label - prediction
total_error += error
self.weights[1:] += self.learning_rate * error * inputs
self.weights[0] += self.learning_rate * error
self.errors.append(total_error)

if __name__ == "__main__":
# Example usage:
training_data = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
labels = np.array([0, 1, 1, 1])
perceptron = Perceptron(num_inputs=2, learning_rate=0.1, epochs=100)
perceptron.train(training_data, labels)

test_inputs = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])

for inputs in test_inputs:
prediction = perceptron.predict(inputs)
print(f"Input: {inputs}, Prediction: {prediction}")
OUTPUT:
 Experiment-3

Objective: Write a Program to implement full counter propagation

network.
Code:
v=[0.6 0.2; 0.6 0.2;0.2 0.6; 0.2 0.6];
w=[0.4 0.3;0.4 0.3];
x=[0 1 1 0];
y= [1 0];
alpha=0.3;
for j=1:2
D(j) =0;
for i=1:4
D(j) =D(j)+(x(i) -v(i,j)) ^2;
end
for k=1:2
D(j) =D(j)+(y(k) -w(k,j)) ^2;
end
end
for j=1:2
if D(j)==min(D)
J=j;
end
end
disp('After one step the weight matrix are');
v(:,J)=v(:,J)+alpha*(x' -v(: ,J))
w(:,J)=w(:,J)+alpha*(y'-w(:,J))
OUTPUT:
 Experiment-4

Write a MATLAB Script containing four functions Addition, Subtraction,

Multiplication and Division

p=input('Enter the value of first number')

q=input('Enter the value of second number')

function add=ADD(a, b)

add=a+b;

end

function sub=SUB(a, b);

sub=a-b;

end

function multiply=MULTIPLY(a, b);

multiply=a*b;

end

function divide=DIVIDE(a, b);

divide=a/b;

end

fprintf("Addition of two numbers is %d \n", ADD(p,q));

fprintf("Subtraction of two numbers is %d \n", SUB(p,q));

fprintf("Multiplication of two numbers is %d \n", MULTIPLY(p,q));

fprintf("Division of two numbers is %d \n", DIVIDE(p,q));

OUTPUT:
 Experiment-5(a)

Write a M-file to calculate the weights for the following patterns using

hetero associative neural net for mapping four input vectors to two output

vectors.

S1 S2 S3 S4 T1 T2
1 1 0 0 1 0
1 0 1 0 1 0
1 1 1 0 0 1
0 1 1 0 0 1

%Hetero associative neural net for mapping input vectors to output vectors

clc;
clear;
x=[1 1 0 0;1 0 1 0;1 1 1 0;0 1 1 0];
t=[1 0;1 0;0 1;0 1];
w=zeros(4,2);
for i=1:4
w=w+x(i,1:4)'*t(i,1:2);
end
disp('weight matrix');
disp(w);
OUTPUT:
 Experiment-5(b)

Write a MATLAB program to find the weight matrix of an auto associative

net to store the vector(1 1 -1 -1). Test the response of the network by

presenting the same pattern and recognize whether it is a known vector or

unknown vector.

%Autoassociative net to store the vector

clc;

clear;

x=[1 1 -1 -1];

w=zeros(4,4);

w=x'*x;

yin=x*w;

for i=1:4

if yin(i)>0

y(i)=1;

else

y(i)=-1;

end
end

disp('Weight matrix');

disp(w);

if x==y

disp('The vector is a know Vector');

else

disp('The vector is a Unknown Vector');

end
OUTPUT:
 Experiment-5(c)

Write an M-file to store the vector (-1 -1 -1 -1) and (-1 -1 1 1) in an auto

associative net. Find the weight matrix. Test the net with (1 1 1 1 ) as input.

clc;

clear;

x=[-1 -1 -1 -1;-1 -1 1 1];

t=[1 1 1 1];

w=zeros(4,4);

for i=1:2

w=w+x(i,1:4)'*x(i,1:4);

end

yin=t*w;

for i=1:4

if yin(i)>0

y(i)=1;

else

y(i)=-1;

end

end
disp('The calculated weight matrix');

disp(w);

if x(1,1:4)==y(1:4) | x(2,1:4)==y(1:4)

disp('The vector is a Known Vector');

else

disp('The vector is a unknow vector');

end
OUTPUT:
 Experiment-5(d)

Write a MATLAB program to find the weight matrix in bipolar form for

the Bi-directional Associative Memory (BMA) network based on the

following binary input output pairs.

S(1) = (1 1 0) t1(1) = (1 0)

S(2) = (1 0 1) t(2) = (0 1)

%Bidirectional Associative Memory neural net

clc;

clear;

s=[1 1 0;1 0 1];

t=[1 0;0 1];

x=2*s-1

y=2*t-1

w=zeros(3,2);

for i=1:2

w=w+x(i,:)'*y(i,:);

end
disp('The calculated weight matrix');

disp(w);

OUTPUT:
 Experiment-6

Write a MATLAB program to store the vector (1 1 1 -1). Find the weight

matrix with no self-connection. Test this using discrete hopfield net with

mistake in first and second component of stored vector i.e. (0 0 1 0) [since

discrete Hopfield net uses binary vectors]. Also the given pattern in binary

form is [1 1 1 0].

clc;

clear;

x=[1 1 1 0];

tx=[0 0 1 0];

w=(2*x'-1)*(2*x-1);

for i=1:4

w(i,i)=0;

end

con=1;

y=[0 0 1 0];

while con
 up=[4 2 1 3];

for i=1:4

yin(up(i))=tx(up(i))+y*w(1:4,up(i));

if yin(up(i))>0

y(up(i))=1;

end

end

if y==x

disp('convergence has been obtained');

disp('converged output');

disp(y);

con=0;

end

end
OUTPUT: