What are the reasons for having different outputs after several runs?

Question

Sanaz 2013-9-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/87052-what-are-the-reasons-for-having-different-outputs-after-several-runs

评论： Greg Heath 2013-9-29

I use the same initial condition for my network, but I still get different outputs. What are the other factors that can cause this difference?

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 2013-9-14

2
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/87052-what-are-the-reasons-for-having-different-outputs-after-several-runs#answer_96731

编辑：Greg Heath 2013-9-14

在 MATLAB Online 中打开

The short answer is that train(only if all weights are zero) or configure( anytime) assign weights depending on the state of the RNG.

If you are training in a loop over random initial weights. The best statistically unbiased choice for the best net is determined by the minimum mse of the validation set.

 rng(4151941)             % Initialize RNG with famous birthday
 for i = 1:Ntrials
   s{i} = rng;            %Save the ith state of the rng (may not need a cell) 
   net  = configure(net,x,t);
   [ net tr ] = train(net,x,t);
    mseval(i) = tr.best_vperf;  % Best mseval over all epochs of ith run
 end
 [ minmseval ibest ] = min(mseval);
 rng     = s{ibest};            % For repeating the best design
 bestnet = configure(net,x,t);
 bestIW0 = bestnet.IW
 bestb0  = bestnet.b
 bestLW0 = bestnet.LW
 [ bestnet tr ] = train(bestnet,x,t) % NO SEMICOLON TO REVEAL ALL DETAILS!!!

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

Walter Roberson 2013-9-12

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/87052-what-are-the-reasons-for-having-different-outputs-after-several-runs#answer_96601

By default, Neural Networks are initialized randomly.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Walter Roberson 2013-9-12

http://www.mathworks.com/matlabcentral/answers/22100

Greg Heath 2013-9-29

编辑：Greg Heath 2013-9-29

The obsolete newfit, newpr and newff initialize when the net is created.

The current fitnet, patternnet and feedforwardnet are either initialized by configure before training OR, if configure is not used, they will be automatically initialized by train.

In the latter case it is difficult to obtain those values. If you really need them, use configure then save or print the weights before calling train.

请先登录，再进行评论。