How create NN ???

2 次查看（过去 30 天）
Silva Doo
Silva Doo 2018-4-16
编辑： Greg Heath 2019-2-4
How many layers are hidden ? 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);

请先登录，再回答此问题。

采纳的回答

BERGHOUT Tarek
BERGHOUT Tarek 2019-2-4
编辑：Greg Heath 2019-2-4
there are 2 hidden layers .
but you should know that there is a difference between the training method and the type of the network ;
back propagation is a training tool to NN , you can't say that it is a backpropagation network , because many different types of nets can be trained with back propagation

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by