What are the dimensions mentioned in fully connected layer stands for (D, N and S) ?

In fullyConnectedLayer documentation, it is written that: "... X of size D-by-N-by-S, then the fully connected layer outputs an array Z of size outputSize-by-N-by-S. At time step t, the corresponding entry of Z is WXt+b, where Xt denotes time step t of X." , what (D, N and S) stand for?

Link: https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.fullyconnectedlayer.html#

Regards,

Oytun GUNES

[OYTUN GUNES]

Okay I think I found from lstm documentation as; D stands for dimension of hidden units, S is the length of sequence, but still what is N?

https://www.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html

Regards,

Oytun

Answer 1

[Srivardhan Gadila]

N stands for number of observations (or sequences).

For more information you can refer to:

1. sequences Input Argument of the function trainNetwork
2. Invalid training data. X and Y must have the same number of observations