MATLAB Answers

First Neural Network Using XOR

19 views (last 30 days)
Darryl
Darryl on 25 Feb 2013
I am trying to implement a simple XOR network. All is okay once the input and target data has been setup, but as soon as I try and train the network I get the Neural Network Training Tool window open, but the "stop training" and "cancel" button are shaded out with "minimum gradient reached". As soon as I try and simulate the network, the XOR_NET_output data is wrong and there seems to be error data within the XOR_NET_errors.
I can provide more data if necessary.

  1 Comment

Shashank Prasanna
Shashank Prasanna on 25 Feb 2013
Since this is a fairly simple setup, could you share your data and the lines of code you've written? It will be easier to look into the issue.

Sign in to comment.

Accepted Answer

Greg Heath
Greg Heath on 27 Feb 2013
Edited: Greg Heath on 27 Feb 2013
I have many posts on the NEWSGROUP, ANSWERS and comp.ai.neural-nets re XOR. Most can be retreived by searching on
greg xor
The minimal configuration has a 2-2-1 topology with Nw = (2+1)*2+(2+1)*1 = 9 unknown weights to be estimated with only 4 equations. Consequently, there are an infinite number of solutions.
Nevertheless, I recall a success rate of only ~ 70% when training from a random set of initial weights generated by MATLAB's default NW algorithm.
So, just try 10 or more different random weight initializations. You should get at least 5 successful solutions.
Hope this helps.
Thank you for formally accepting my answer.
Greg

  0 Comments

Sign in to comment.

More Answers (1)

Mohan
Mohan on 26 Feb 2013
The implementation of the XOR with neural networks is clearly explained with Matlab code in "Introduction to Neural Networks Using Matlab 6.0 " by S. N. Sivanandam, S. N Deepa

  0 Comments

Sign in to comment.

Sign in to answer this question.

Products