Contents

cascadeforwardnet

Cascade-forward neural network

Syntax

cascadeforwardnet(hiddenSizes,trainFcn)

Description

Cascade-forward networks are similar to feed-forward networks, but include a connection from the input and every previous layer to following layers.

As with feed-forward networks, a two-or more layer cascade-network can learn any finite input-output relationship arbitrarily well given enough hidden neurons.

cascadeforwardnet(hiddenSizes,trainFcn) takes these arguments,

hiddenSizes

Row vector of one or more hidden layer sizes (default = 10)

trainFcn

Training function (default = 'trainlm')

and returns a new cascade-forward neural network.

Examples

Here a cascade network is created and trained on a simple fitting problem.

[x,t] = simplefit_dataset;
net = cascadeforwardnet(10);
net = train(net,x,t);
view(net)
y = net(x);
perf = perform(net,y,t)
perf =

   1.9372e-05

Was this topic helpful?