Multilayer neural network with newff
2 ビュー (過去 30 日間)
古いコメントを表示
Hello everyone! I have constructed a neural network with 2 input layers and 3 layers (one of them represents the output one). net.inputLayer{1} is connected to layer{1} and inputLayer{2} is connected to Layer{2}. I want input layers 1,2 to have specific subset of my input data. How can i do this and then train the network with newff?
Thanks in advance for your feedback!!
0 件のコメント
採用された回答
Greg Heath
2016 年 5 月 25 日
If you are new with NNs stick with the defaults as much as possible. Input-Hidden-Output is sufficient for a universal approximator. It is very seldom that more is needed.
Although NEWFIT (regression) and NEWPR(classification) that call NEWFF (generic) are still available, they all are obsolete.
Do you have access to the current functions FITNET(regression) and PATTERNNET(classification) that call FEEDFORWARDNET (generic)? If so, choose one of the first two.
First practice on the MATLAB examples in the help and doc documentation.
First accept all defaults. If that doesn't work, increase the number of hidden nodes.
Don't hesitate to consult us again if you need help.
Hope this helps.
Greg
More examples can be obtained from
help nndatasets
doc nndatasets
Hope this helps.
Greg
0 件のコメント
その他の回答 (1 件)
参考
カテゴリ
Help Center 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!