Scribd
Upload
48 views2 pages

Assig Report Ex 2

This document describes an experiment using a neural network in MATLAB to approximate the XOR problem. It designs a neural network using a bipolar sigmoid activation function. The code initializes weights and biases, trains the network over multiple epochs using backpropagation, and calculates the root mean squared error (RMSE) as a performance index. A plot shows the RMSE decreasing with increasing number of iterations until it reaches below 0.005, at which point training stops.

Uploaded by

prakash
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
48 views2 pages

Assig Report Ex 2

This document describes an experiment using a neural network in MATLAB to approximate the XOR problem. It designs a neural network using a bipolar sigmoid activation function. The code initializes weights and biases, trains the network over multiple epochs using backpropagation, and calculates the root mean squared error (RMSE) as a performance index. A plot shows the RMSE decreasing with increasing number of iterations until it reaches below 0.005, at which point training stops.

Uploaded by

prakash
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

JAYPEE UNIVERSITY OF ENGINEERING AND TECHNOLOGY

ECE DESIGN AND SIMULATION LAB II REPORT


EXPERIMENT NO:2
AIM: Design a Neural network for approximation of XOR problem in MATLAB and
compare the performance index (RMSE) based on following parameters. Using bipolar
sigmoidal function.
SOFTWARE USED : Mat Lab 7.0
CODE :
clear all; close all;
c=1;
n=2;
m=1;
h=4;
N=4;
v=[0.197 0.3191 -0.1448 0.3394; 0.3099 0.1904 -0.0347 -0.4861];
v1=zeros(n,h);
w=[-0.3387 ; 0.2771 ; 0.2859; -0.3329];
w1=zeros(h,m);
b1=[-.3378 0.2771 0.2859 -0.3329];
b2=-0.1401;
x=[1 1 -1 -1 ; 1 -1 1 -1];
t=[-1 1 1 -1 ];
alpha=0.3;
mf=0.9;
con=1;
epoch=0;
while con
e=0;
EE=0;
for I=1:N
for j=1: h
zin(j)=b1(j);
for i=1:n
zin(j)=zin(j)+x(i,I)*v(i,j);
end
z(j)=bipsig(zin(j));
end

17

yin=b2+z*w;
y(I)=bipsig(yin);
delk=(t(I)-y(I))*bipsig1(yin);
delw=alpha*delk*z'+mf*(w-w1);
delb2=alpha*delk;
delinj=delk*w;

Page

for j=1:h
delj(j,1)=delinj(j,1)*bipsig1(zin(j));

REPORT BY PRAKASH CHANDRA BHARTI

APR 2012

JAYPEE UNIVERSITY OF ENGINEERING AND TECHNOLOGY


ECE DESIGN AND SIMULATION LAB II REPORT
end
for j=1:h
for i=1:n
delv(i,j)=alpha*delj(j,1)*x(i,I)+mf*(v(i,j)-v1(i,j));
end
end
delb1=alpha*delj;
w1=w;
v1=v;
w=w+delw;
b2=b2+delb2;
v=v+delv;
b1=b1+delb1';
e=e+(t(I)-y(I))^2;
end
Rmse=(sqrt(e))/N;
if e<0.005
con=0;
end
epoch=epoch+1;
xl1(epoch)=epoch;

end
disp ('Rmse')
disp(Rmse)
plot(xl1,yl1,'-+b')

0.6

0.5

RMSE

if epoch==50000
con=0;
end
if (epoch<60000)
yl1(epoch)=Rmse;
end

NO OF ITERATION VS RMSE
0.7

0.4

0.3

0.2

0.1

20

40

60
80
NO OF ITERATION

100

120

Page

18

FIG : NO OF ITERATION VS RMSE

140

REPORT BY PRAKASH CHANDRA BHARTI

APR 2012

You might also like