How to choose the number of neurons in the hidden layer of neural network?

Question

afef 2017-6-3

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/343156-how-to-choose-the-number-of-neurons-in-the-hidden-layer-of-neural-network

评论： afef 2017-6-6

Hi, i'm using the neural network for classification using nnstart and i have dataset (input) with a size of 9*981 and i want to know how to choose the number of neurons in the hidden layer for it ?

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 2017-6-5

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/343156-how-to-choose-the-number-of-neurons-in-the-hidden-layer-of-neural-network#answer_269569

在 MATLAB Online 中打开

Use trial and error with the training subset goal

 MSEtrngoal = 0.01*var(trntarget,1)        % 1-D target
 or
 MSEtrngoal = 0.01*mean(var(trntarget',1)) % Otherwise

Start with the MATLAB default H = 10 and design ~10 nets for each setting of H. Each of the 10 is initialized with a different setting of random initial weights.

Hope this helps

Thank you for formally accepting my answer

Greg

2 个评论
显示无隐藏无

afef 2017-6-5

在 MATLAB Online 中打开

This is the script that i got after using nnstart

x = inputpatient';
t = targetpatient';
 % Choose a Training Function
% For a list of all training functions type: help nntrain
% 'trainlm' is usually fastest.
% 'trainbr' takes longer but may be better for challenging problems.
% 'trainscg' uses less memory. Suitable in low memory situations.
trainFcn = 'trainscg';  % Scaled conjugate gradient backpropagation.
 % Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
 % Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
 % Train the Network
[net,tr] = train(net,x,t);
 % Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
tind = vec2ind(t);
yind = vec2ind(y);
percentErrors = sum(tind ~= yind)/numel(tind);
 % View the Network
view(net)
 % Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
%figure, plottrainstate(tr)
%figure, ploterrhist(e)
%figure, plotconfusion(t,y)
%figure, plotroc(t,y)

and i tried to change the hiddenLayerSize to improve the accuracy of the network and i got this confusion matrix

And i still can't achieve the good accuracy . So what can i do please ?

afef 2017-6-6

https://www.mathworks.com/matlabcentral/answers/343156-how-to-choose-the-number-of-neurons-in-the-hidden-layer-of-neural-network#answer_269569

Dear Greg Heath sorry but i don't where should i add the code for trial and error that you told me to add in my script and you mean by default H = 10 the number of neurons in the hidden layer??? I really will appreciate if you answer me .

请先登录，再进行评论。