nndata

(To be removed) Create neural network data

nndata 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

nndata(N,Q,TS,v)


Description

nndata(N,Q,TS,v) takes these arguments,

N	Vector of M element sizes
Q	Number of samples
TS	Number of timesteps
v	Scalar value

and returns an M-by-TS cell array where each row i has N(i)-by-Q sized matrices of value v. If v is not specified, random values are returned.

You can access subsets of neural network data with getelements, getsamples, gettimesteps, and getsignals.

You can set subsets of neural network data with setelements, setsamples, settimesteps, and setsignals.

You can concatenate subsets of neural network data with catelements, catsamples, cattimesteps, and catsignals.

Examples

Here four samples of five timesteps, for a 2-element signal consisting of zero values is created:

x = nndata(2,4,5,0)

To create random data with the same dimensions:

x = nndata(2,4,5)

Here static (1 timestep) data of 12 samples of 4 elements is created.

x = nndata(4,12)

Version History

Introduced in R2010b

R2026a: nndata will be removed

nndata will be removed in a future release.

To learn more about data processing for neural networks, see these examples and topics:

• Preprocess Data for Domain-Specific Deep Learning Applications

• Datastores for Deep Learning

• Choose an App to Label Ground Truth Data

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