create an XOR GATE using a feed forward neural net

138 views (last 30 days)
Hello I am new to neural networrks in matlab.And I want to create a feedforward neural net to calculate XORs of two input values.
The theoretical neural network is given below in the pic.I want to replicate the same using matlab neural net toolbox.
for this i have created a simple neural network
net=feedforwardnet(2);
since i need two inputs A and B I have changed the inputs as the following code:
net.numInputs=2;
view(net);
After running the code I am getting the following figure:
The matlab representation for neural network is quite different than the theoretical one. Now i can't understand why the second input is not connected .I need to specify the input values for A[0 0 1 1 ] and B[0 1 0 1] so that i get the out put as t[0 1 1 0] which is XOR.Kindly explain me how t set the bias as magnitude one and the weights for the branches as in the theoretical figure to the same as in my neural network in matlab.

Accepted Answer

Greg Heath
Greg Heath on 16 Mar 2016
You are mistaken. You should only use 1 input. However, it should be two dimensional.
Hope this helps.
Thank you for formally accepting my answer*
Greg
  1 Comment
Newman
Newman on 16 Mar 2016
Edited: Newman on 16 Mar 2016
Sir r u trying to say that my input x should be in this form:
[0 0 1 1;0 1 0 1].
But sir can you please tell me how should i change the weights and set the biases ?

Sign in to comment.

More Answers (2)

Aya Ahmed
Aya Ahmed on 24 Apr 2020
Newman have you reach to the code ??
PLZ help me , i want to make that but i cant

Multi Vac
Multi Vac on 26 Apr 2020

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by