How use trainNetwork function for feedforward custom net ?
古いコメントを表示
Hi all,
I need to train feedforward neural network with RMSProp or Adam optimization algorithm. I have the custom configuration of number of hidden layers and neurons. How can I do it using matlab ? I founded two different functions for training: 'train' and 'trainNetwork'. The first function is used for feedforward network, but hasn't RMSProp or Adam optimizers. The second function - has needed optimizers, but as I understood work only with CCN, and you can't configure custom feedforward NN.
Please correct me if I'm wrong or suggest any solutions.
Best Regards, Artyom
回答 (0 件)
カテゴリ
ヘルプ センター および File Exchange で Deep Learning Toolbox についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!