MATLAB: Coding ANN learning parameters (e.g number of hidden neurons, learning methods, learning rate, momentum, number of epoch) in Genetic Algorithm chromosome

genetic algorithms coding ann parameters

how I can code of ANN learning parameters (e.g number of hidden neurons, learning methods, learning rate, momentum, number of epoch) in Genetic Algorithm chromosome? Iam looking for a matlab code or software

Best Answer

Search both NEWSGROUP and ANSWERS using

 greg genetic
 Hope this helps

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to generate chromosome

Is maybe this what are you looking for?

chromo=40;
gene=20;
for i=1:1:chromo
    for j=1:1:gene
    pop=randi([0,1]);
    A(:,j)=[pop]
    end
    B(i,:)=A(:,j)
end
[m,n]=size(B) %just for test

B is matrix with m=40 and n=20, so you have 40 choromosomes with each having 20 genes.

Best of luck.

MATLAB: How to change learning rate and momentum in ‘trainlm’ neural network

use

options = trainingOptions('sgdm',...
    'MaxEpochs',60, ...
    'LearnRateDropFactor',0.1,...
    'LearnRateDropPeriod',1,...
    'LearnRateSchedule','piecewise',...
    'ValidationData',{valImages,valLabels},...
    'ValidationFrequency',50,...
    'Momentum',0.85,...
    'ValidationPatience',5,...
    'InitialLearnRate',0.1,...
    'MiniBatchSize',128,...
    'Verbose',true,...
    'executionenvironment','cpu',...
    'Shuffle','every-epoch',...
    'Plots','training-progress');
net = trainNetwork(...,...,...,options);

and choose the parameters accordingly.

For default values, see the docs of trainingOptions.

In terms of the learning rate and momentum, I typically start with a large one just to test the general behaviour and then I drop the learning rate to get more accurate results. Its difficult to give you some concrete advice because the optimal learning rate depends on your specific problem.

Best Answer

Related Solutions

MATLAB: How to generate chromosome

MATLAB: How to change learning rate and momentum in ‘trainlm’ neural network

Related Question