weight and bias values i get from trained neural network is mistake?

Question

Halsey 2019-12-4

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/494799-weight-and-bias-values-i-get-from-trained-neural-network-is-mistake

评论： Alessia Li Noce 2021-4-9

采纳的回答： JESUS DAVID ARIZA ROYETH

在 MATLAB Online 中打开

Hi, i try to get the weight and bias from the neural network that i train.

ActFunc_Hid and ActFunc_Out depends on any activation function i set on hidden and outer layer.

However, when i trained the neural network, i test it again by output = sim(net, a), where a is new input. the shown output is not the same as what i calculate manually based on the weight and bias value got from the trained neural network.

Is there any mistake in my code?

     
       net=newff(input, output, 1,{ActFunc_hid ActFunc_Out});
       [net tr]=train(net,input,output);
       w1 = net.IW{1}
       w2 = net.LW{2}
       b1 = net.b{1} 
       b2 = net.b{2} 
 

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

JESUS DAVID ARIZA ROYETH 2019-12-4

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/494799-weight-and-bias-values-i-get-from-trained-neural-network-is-mistake#answer_404706

在 MATLAB Online 中打开

It is not the same because Matlab does a normalization procedure of the variables so if you want to do it manually it would be like this:

xoffset = net.inputs {1} .processSettings {1} .xoffset;
gain = net.inputs {1} .processSettings {1} .gain;
ymin = net.inputs {1} .processSettings {1} .ymin;
y1 = bsxfun (@ times, bsxfun (@ minus, x, xoffset), gain);
y1 = bsxfun (@ plus, y1, ymin);

y1 is the true entrance to the neural network

2 个评论
显示无隐藏无

Halsey 2019-12-4

thank you so much!

Alessia Li Noce 2021-4-9

Hi,sorry for bring it up after all this time, for the output is the same procedure? I'm doing also a manually implementation and I want to replicate the pre/post processing of newff, which use the mapminmax

请先登录，再进行评论。