Neural Network Classification: cost function, regularization parameter, availability of the hidden layers...

Question

Richard Palmer 2015-5-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/219760-neural-network-classification-cost-function-regularization-parameter-availability-of-the-hidden

评论： Richard Palmer 2015-5-28

采纳的回答： Greg Heath

How do I derive the cost function J from a nn classification model?

How can I set a regularization parameter? Is this approached using your weights capability?

Are the hidden layer values available after modeling?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2015-5-28

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/219760-neural-network-classification-cost-function-regularization-parameter-availability-of-the-hidden#answer_180739

在 MATLAB Online 中打开

You cannot derive a cost function from a model.

You specify the cost function for a design.

If you are new at this, start out by accepting the NNToolbox defaults. First check out the relatively simple examples in the classification documentation

 help patternnet
 doc patternnet

Then search the NEWSGROUP and ANSWERS for posted examples. For example

greg patternnet

The default transfer functions are tansig (hidden layer) and softmax (output layer)

The "cost" function is crossentropy

Many questions on terminology and details can be obtained using the commands help, doc and type, e.g.,

 help patternnet
 doc patternnet
 type patternnet

Hope this helps.

Thank you for formally accepting my answer

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Richard Palmer 2015-5-28

在 MATLAB Online 中打开

Thanks for your response. I still have some questions. I believe that I know the formulae for the cost functions for the models in the toolkit. For instance, the cost function for a regularized LR function is

(Sum(h(xi)-yi)**2 + lambda sum(theta**2))/(2 m)

for a regularized linear regression. I would like to retrieve the theta coefficients and want to know how to set the lambda (regularization) parameter.

The unregularized cost function will give different values for the training/evaluation/test sets. Can the crossentropy function be decomposed into it's constituent parts?

If this is in the documentation, I apologize. I haven't found the information at this point.

Again, thanks for replying.

请先登录，再进行评论。