Design of Perceptron AND network and program of Perceptron Training Algorithm

Design of Perceptron AND network and program of Perceptron Training Algorithm

Soft Computing

PROGRAM :

% Perceptron for AND Function 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 0.

epoch=epoch+1;

 end

disp('Perceptron for AND Function');

 disp('Final Weight Matrix');

 disp(w);

 disp('Final Bias');

 disp(b);

disp('Perceptron for AND Function');

disp('Final Weight Matrix');

 disp(w);

disp('Final Bias');

 disp(b);

OUTPUT :

Enter Learning rate=1

Enter Threshold Value=0.5

 Perceptron for AND Function

Final Weight Matrix

 1 1

OUTPUT:

ANDNet_errors =     0     0     0     0

>> ANDNet_outputs

ANDNet_outputs =     0     0     0     1

>> ANDNet.iw{1,1}

ans =     2     1

>> ANDNet.b{1}

ans =    -3