Weight decay parameter and Jacobian matrix of a neural network

Question

Platon 2014-2-19

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/116772-weight-decay-parameter-and-jacobian-matrix-of-a-neural-network

评论： Greg Heath 2014-2-21

采纳的回答： Greg Heath

I want calculate prediction intervals so I have 2 direct questions:

How can I get the weight decay parameter 'alpha' (mse+alpha*msw) used when using 'trainbr' as a training algorithm?
How can I get the neural network jacobian matrix (derivatives following weights) calculated during training?

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 2014-2-19

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/116772-weight-decay-parameter-and-jacobian-matrix-of-a-neural-network#answer_124974

编辑：Greg Heath 2014-2-19

在 MATLAB Online 中打开

The documentation for trainbr is pretty bad.

 help trainbr
 doc trainbr

Look at the source code

type trainbr

I am not familiar with it but will take a look when I get time.

Meanwhile, if you make a run, the training record tr, contains 2 parameters

             gamk: [1x31 double]
             ssX:  [1x31 double]

that are involved.

Hope this helps.

Thank you for formally accepting my answer

Greg

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。

Answer 2

Platon 2014-2-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/116772-weight-decay-parameter-and-jacobian-matrix-of-a-neural-network#answer_125196

Thank you. It helps to determine alpha but not to calculate the neural network jacobian matrix. Hope that future Matlab NN tool Box versions include specific tools to make prediction interval study.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2014-2-21

When using the obsolete msereg and mse with the regularization option, the weight parameters are alpha (specified error weight) and (1-alpha).

However when using trainbr, the weight parameters alpha and beta are calculated each epoch. Haven't decifered the logic yet. Might be faster to search the web.

请先登录，再进行评论。