OR Perceptron
clear;
clc;
% Input data (4 samples with 2 features each)
x = [1 1 -1 -1; 1 -1 1 -1];
% Desired output (OR function)
t = [1 1 1 -1];
% Initialize weights and bias
w = [0 0];
b = 0;
alpha = input('Enter learning rate: ');
theta = input('Enter the threshold: ');
converged = false;
epoch = 0;
while ~converged
converged = true; % Assume convergence until proven otherwise
for i = 1:4
yin = b + w * x(:, i);
% Activation function (step function)
if yin <= theta
y = -1;
else
y = 1;
end
if y ~= t(i)
converged = false; % We need to keep training
w = w + alpha * (t(i) - y) * x(:, i)';
b = b + alpha * (t(i) - y);
end
end
epoch = epoch + 1;
end
disp('Perceptron OR function');
disp(['Epochs required for convergence: ' num2str(epoch)]);
disp('Final Weight Matrix:');
disp(w);
disp('Final Bias:');
disp(b);
Enter learning rate:
1
Enter the threshold:
1
Perceptron OR function
Epochs required for convergence: 2
Final Weight Matrix:
2 2
Final Bias:
2
AND Perceptron
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 the threshold: ');
converged = false;
epoch = 0;
while ~converged
converged = true; % Assume convergence until proven otherwise
for i = 1:4
yin = b + x(1, i) * w(1) + x(2, i) * w(2);
% Activation function (step function)
if yin <= theta
y = -1;
else
y = 1;
end
if y ~= t(i)
converged = false; % We need to keep training
for j = 1:2
w(j) = w(j) + alpha * (t(i) - y) * x(j, i);
end
b = b + alpha * (t(i) - y);
end
end
epoch = epoch + 1;
end
disp('Perceptron for AND function');
disp(['Epochs required for convergence: ' num2str(epoch)]);
disp('Final Weight Matrix:');
disp(w);
disp('Final Bias:');
disp(b);
Enter learning rate:
0.1
Enter the threshold:
0.5
Perceptron for AND function
Epochs required for convergence: 2
Final Weight Matrix:
0.2000 0.2000
Final Bias:
0.2000
AND Function using MC Culloch
clear;
clc;
disp('Enter the Weights');
w1 = input('Weight w1=');
w2 = input('Weight w2=');
disp('Enter the theta');
theta = input('theta=');
y = [0 0 0 0];
x1 = [1 1 0 0];
x2 = [1 0 1 0];
z = [1 0 0 0];
con = 1;
while con
zin = x1 * w1 + x2 * w2; % Fixed the calculation of zin
for i = 1:4
if zin(i) >= theta
y(i) = 1;
else
y(i) = 0;
end
end
disp('Output of net');
disp(y);
if isequal(y, z) % Changed '==' to 'isequal' for array comparison
con = 0;
else
disp('Net is not learning');
w1 = input('weight w1=');
w2 = input('weight w2=');
theta = input('theta=');
end
end
disp('McCulloch AND function'); % Corrected spelling
disp('Weights of neuron');
disp(w1);
disp(w2);
disp('Threshold value');
disp(theta);
Enter the Weights
Weight w1=
1
Weight w2=
1
Enter the theta
theta=
2
Output of net
1 0 0 0
McCulloch AND function
Weights of neuron
1
Threshold value
2
OR Function using MC Culloch
clear;
clc;
disp('Enter the weight');
w1=input('Weight w1=');
w2=input('Weight w2=');
disp('Enter threshold value');
theta=input('theta=');
y=[0 0 0 0];
x1=[1 1 0 0];
x2=[1 0 1 0];
z=[1 1 1 0];
con=1;
while con
zin=x1*w1+x2*w2;
for i=1:4
if zin(i)>=theta
y(i)=1;
else
y(i)=0;
end
end
disp('Output of net=');
disp(y);
if y==z
con=0;
else disp('Net is not learning Enter another set of weights and threshold
value');
w1=input('Weigth w1=');
w2=input('Weigth w2=');
theta=input('theta=');
end
end
disp('Mc Culluch pitts net for OR function');
disp('Weight of neuron');
disp(w1);
disp(w2);
disp('threshold value=');
disp(theta);
Weigth w1=
1
Weigth w2=
1
theta=
1
Output of net=
1 1 1 0
Mc Culluch pitts net for OR function
Weight of neuron
1
threshold value=
1
XOR function using mc Culloch
clear;
clc;
disp('Enter the weights');
w11 = input('Weight w11=');
w12 = input('Weight w12=');
w21 = input('Weight w21=');
w22 = input('Weight w22=');
v1 = input('Weight v1=');
v2 = input('Weight v2=');
disp('Enter threshold value');
theta = input('Theta=');
x1 = [0 0 1 1];
x2 = [0 1 0 1];
z = [0 1 1 0];
converged = false;
while ~converged
zin1 = x1 * w11 + x2 * w12;
zin2 = x1 * w21 + x2 * w22;
y1 = zeros(1, 4);
y2 = zeros(1, 4);
for i = 1:4
if zin1(i) >= theta
y1(i) = 1;
end
if zin2(i) >= theta
y2(i) = 1;
end
end
yin = y1 * v1 + y2 * v2;
y = zeros(1, 4);
for i = 1:4
if yin(i) >= theta
y(i) = 1;
end
end
if isequal(y, z)
converged = true;
else
disp('Net is learning');
w11 = input('Weight w11=');
w12 = input('Weight w12=');
w21 = input('Weight w21=');
w22 = input('Weight w22=');
v1 = input('Weight v1=');
v2 = input('Weight v2=');
theta = input('Theta=');
end
end
disp('McCulloch XOR function');
disp('Weights of the neuron:');
disp(['w11 = ' num2str(w11)]);
disp(['w12 = ' num2str(w12)]);
disp(['w21 = ' num2str(w21)]);
disp(['w22 = ' num2str(w22)]);
disp(['v1 = ' num2str(v1)]);
disp(['v2 = ' num2str(v2)]);
disp(['Theta = ' num2str(theta)]);
Enter the weights
Weight w11=
1
Weight w12=
-1
Weight w21=
-1
Weight w22=
1
Weight v1=
1
Weight v2=
1
Enter threshold value
Theta=
1
McCulloch XOR function
Weights of the neuron:
w11 = 1
w12 = -1
w21 = -1
w22 = 1
v1 = 1
v2 = 1
Theta = 1
