help me ? How many layers?
显示 更早的评论
How many layers are hidden and output ? Is it Backpropagation network ?
net = newff(minmax(alphabet),[S1 10 S2],{'logsig' 'logsig' 'logsig' },'traingdx');
net.LW{2,1} = net.LW{2,1}*0.01;
net.b{2} = net.b{2}*0.01;
net.performFcn = 'mse';
net.trainParam.show = 20;
net.trainParam.epochs = 2000;
net.trainParam.mc = 0.95;
P = alphabet;
T = targets;
[net,tr] = train(net,P,T);
回答（1 个）
Greg Heath
2018-5-14
编辑：Greg Heath
2018-5-14
1. ONE HIDDEN LAYER IS ALWAYS SUFFICIENT! 2. NEWFF is obsolete, Do you have FITNET?
help fitnet
doc fitnet
2. If you are really serious about getting help, use the example data in
help newff %or help fitnet
and
doc newff %or doc fitnet
Additional data can be obtained from
help nndatasets
and
doc nndatasets
Greg
类别
在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息
2018-5-14
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
