First Neural Network Using XOR
5 ビュー (過去 30 日間)
古いコメントを表示
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 件のコメント
Shashank Prasanna
2013 年 2 月 25 日
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.
採用された回答
Greg Heath
2013 年 2 月 27 日
編集済み: Greg Heath
2013 年 2 月 27 日
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 件のコメント
その他の回答 (1 件)
Mohan
2013 年 2 月 26 日
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 件のコメント
参考
カテゴリ
Help Center および File Exchange で Sequence and Numeric Feature Data Workflows についてさらに検索
製品
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!