reproducibility of results using neural networks

Question

Multi Vac 2011-5-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/7279-reproducibility-of-results-using-neural-networks

I am using 'newff' to create a neural network, 'trainParam' to set its parameters, and 'train' to train it. The problem is that it uses random initial weight values during each time the function is used so that I get different convergence results at different runs using the same data. How do I get reproducibility of the results?

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

Walter Roberson 2011-5-12

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/7279-reproducibility-of-results-using-neural-networks#answer_10011

Provide enough training data that the random initial weights have no impact. Or don't use random initial weights.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2011-11-26

I assume by reproducibility, the OP means exactly the same weights and thresholds. There are many local minima in weight space.

For an I-H-O FFMLP each solution is equivalent to 2^H * H! -1 other solutions obtained by changing weight signs (2^H) and/or reshuffling the order of the hidden nodes (H!)

Therefore, reproducibility requires using the same initial state of rand before creating the net via newff.

Hope this helps.

Greg

请先登录，再进行评论。

Answer 2

Flo Trentini 2011-11-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/7279-reproducibility-of-results-using-neural-networks#answer_29098

I am using 'initzero' for input , layers and biases weights, then i use net = init(net) before training the network. And yet each run gives me different results. How is that possible ?