How to get Gradient from Network Created by Neural Network Toolbox?

2013 6 3
2 个回答
回答已采纳
更新时间：2017 12 20
5 次查看（30 天）

0 个投票

How can the gradient of the performance function with respect to the weights and biases of a neural network created by the Neural Network Toolbox be obtained? I am looking for a function analogous to "getwb".
[x,t] = simplefit_dataset;
net = feedforwardnet(10);
net = train(net,x,t);
wb = getwb(net);
gwb = ????; % something analogous to getwb(net)
% resulting in a 31x1 vector
Thanks, Ahmed

请先登录，再回答此问题。

 采纳的回答

Ahmed
Ahmed 2013-6-6

0 个投票

Actully, the function 'staticderivative' can do this for a static network. In general, however, it is likely that defaultderiv is the better choice.
help defaultderiv
help staticderiv

更多回答（1 个）

Greg Heath
Greg Heath 2013-6-3

1 个投票

[x,t] = simplefit_dataset;
net = fitnet; % No need for feedforwardnet
rng(0) % Convenient for duplicating the run
[ net tr ] = train(net,x,t);
wb = getwb(net);
tr = tr % No semicolon...Look at all of the goodies!
stopcrit = tr.stop
bestepoch = tr.best_epoch
gradient = tr.gradient; %complete history
Hope this helps
Thank you for formally accepting my answer
Greg ;

7 个评论
显示 5更早的评论 隐藏 5更早的评论

Ahmed
Ahmed 2013-6-4
Thank you for your reply, Greg. The gradient in the "tr" structure is not the gradient of the performance with respect to the weights and biases. The vector contains one element per training iteration. It seems to be something like the gradient magnitude. The solution I am looking for would yield a vector of the same size as "wb", in this example 31x1.
Greg Heath
Greg Heath 2013-6-4
Either output wb every epoch or dig into the source code of trainlm.
Ahmed
Ahmed 2013-6-6
'wb' would be the vector containing the current weight/bias coefficients and not the gradient of the performance.
Greg Heath
Greg Heath 2013-6-8
Yes. Then approximate the derivatives with finite differences. {Novel idea!)
Zheng Chai
Zheng Chai 2017-12-19
Hi Greg, sorry to bother you but do you know how to get the weights and biases after each epoch? I mean record the w&b within training. You mentioned dig into the source code of trainlm, can you help me with where to insert my command in trainlm? I am a beginner and know little about matlab. Many thanks.
Greg Heath
Greg Heath 2017-12-19
编辑：Greg Heath 2017-12-19
Sorry, Each year it seems that MATLAB modifies code, presumably to make it better in some esoteric way.
However an annoying result is that the code has become more and more difficult for the average user to understand.
Greg
PS Try contacting MATLAB directly.
Zheng Chai
Zheng Chai 2017-12-20
Thank you so much Greg. Indeed Matlab modified its code. I could not find a proper helper function in my R2013b, but after updating it to R2017b, I found it. Thank you again for your kind help.

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by