con2seq (Neural Network Toolbox)

Convert concurrent vectors to sequential vectors

s = con2seq(b)

The neural network toolbox arranges concurrent vectors with a matrix, and sequential vectors with a cell array (where the second index is the time step).

con2seq and seq2con allow concurrent vectors to be converted to sequential vectors, and back again.

con2seq(b)takes one input,

b - R x TS matrix.

and returns one output,

S - 1 x TS cell array of R x 1 vectors.

con2seq(b,TS) can also convert multiple batches,

b - N x 1 cell array of matrices with M*TS columns.

TS - Time steps.

and will return,

S - N x TS cell array of matrices with M columns.

Examples

Here a batch of three values is converted to a sequence.

p1 = [1 4 2]
p2 = con2seq(p1)

Here two batches of vectors are converted to two sequences with two time steps.

p1 = {[1 3 4 5; 1 1 7 4]; [7 3 4 4; 6 9 4 1]}
p2 = con2seq(p1,2)