neural network training algorithms
Afficher commentaires plus anciens
i have to train network with 12 different training algorithms but i am facing issues
Arch = [10 3];
numHiddenNeurons=10;
brainNet = newff(Ranges, Arch, {'tansig','purelin'},'trainlm');
brainNet.trainParam.epochs = 100;
brainNet.trainParam.lr = 0.9;
brainNet.trainParam.learnFcn = 'learngdm';
brainNet.trainParam.mc = 0.9;
brainNet5000_D_br = train(brainNet, TrainSet, TrainOut);
when i train the network with levenberg algorithm and bayesian regularization it works well.but when i apply other algorithms such as gradient decent "gdm,gd,bfg,scg,etc" it give error and not display any result.please help me regarding algos syntax what changes should i make for every algo.
Réponses (0)
Catégories
En savoir plus sur Pattern Recognition dans Centre d'aide et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!