What do these Matlab LSTM parameters means and used for

Question

Ahmad Kamal Bin Mohd Nor 2019년 10월 10일

답변: Divya Gaddipati 2019년 10월 22일

Hi there

Been trying to understand these parameter in LSTM (what are they used for);

numHiddenUnits

fullyConnectedLayers(Output Size) --> what is Output Size for a sequence to sequence regression?

Answer 1

Divya Gaddipati 2019년 10월 22일

Hi,

numHiddenUnits -

This corresponds to the amount of information remembered between time steps (the hidden state). The hidden state can contain information from all previous time steps, regardless of the sequence length.

If the number of hidden units is too large, then the layer might overfit to the training data.

Output Size in fullyConnectedLayer -

In case of sequence to sequence regression, it refers to the length of the output sequence.