Create neural network data
nndata(N,Q,TS,v)
nndata(N,Q,TS,v) takes these arguments,
N | Vector of |
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.
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)
fromnndata | nndata2sim | nnsize | sim2nndata | tonndata