adddelay

(To be removed) Add delay to neural network response

adddelay will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

net = adddelay(net,n)


Description

net = adddelay(net,n) takes these arguments,

net	Neural network
n	Number of delays

and returns the network with input delay connections increased, and output feedback delays decreased, by the specified number of delays n. The result is a network that behaves identically, except that outputs are produced n timesteps later.

If the number of delays n is not specified, a default of one delay is used.

Examples

Remove and Add Delay to Network

This example shows how to create, train, and simulate a time delay network in its original form, on an input time series X and target series T. Then the delay is removed and later added back. The first and third outputs will be identical, while the second result will include a new prediction for the following step.

Time Delay

[X,T] = simpleseries_dataset;
net1 = timedelaynet(1:2,20);
[Xs,Xi,Ai,Ts] = preparets(net1,X,T);
net1 = train(net1,Xs,Ts,Xi);

y1 = net1(Xs,Xi);
view(net1)

Remove Delay

net2 = removedelay(net1);
[Xs,Xi,Ai,Ts] = preparets(net2,X,T);
y2 = net2(Xs,Xi);
view(net2)

Add Delay

net3 = adddelay(net2);
[Xs,Xi,Ai,Ts] = preparets(net3,X,T);
y3 = net3(Xs,Xi);
view(net3)

Version History

Introduced in R2010b

R2026a: adddelay will be removed

adddelay will be removed in a future release.

To train a neural network with time series data, use one of these options:

• Time Series Modeler app — Interactively design and train neural networks for time series data.

• trainnet — Train neural network. Use this function when you need more flexibility in the network architecture or training algorithm.

To learn more about time series data workflows, see these examples and topics:

• Training Neural Networks with Time Series Data

• Time Series Forecasting Using Deep Learning

• Create and Train NARX Network for Time Series Forecasting

• Long Short-Term Memory Neural Networks

• Example Deep Learning Network Architectures

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.