Main Content

distdelaynet

Distributed delay network

Syntax

distdelaynet(delays,hiddenSizes,trainFcn)

Description

Distributed delay networks are similar to feedforward networks, except that each input and layer weights has a tap delay line associated with it. This allows the network to have a finite dynamic response to time series input data. This network is also similar to the time delay neural network (timedelaynet), which only has delays on the input weight.

distdelaynet(delays,hiddenSizes,trainFcn) takes these arguments,

delays

Row vector of increasing 0 or positive delays (default = 1:2)

hiddenSizes

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

trainFcn

Training function (default = 'trainlm')

and returns a distributed delay neural network.

Examples

collapse all

This example shows how to train a distributed delay neural network to solve a simple time series problem.

[X,T] = simpleseries_dataset;
net = distdelaynet({1:2,1:2},10);
[Xs,Xi,Ai,Ts] = preparets(net,X,T);
net = train(net,Xs,Ts,Xi,Ai);

{"String":"Figure Neural Network Training (31-Aug-2022 01:32:55) contains an object of type uigridlayout.","Tex":[],"LaTex":[]}

view(net)

Y = net(Xs,Xi,Ai);
perf = perform(net,Y,Ts)
perf = 0.0323

Version History

Introduced in R2010b