MATLAB Answers

0

What do these Matlab LSTM parameters means and used for

Ahmad Kamal Bin Mohd Nor さんによって質問されました 2019 年 10 月 10 日
最新アクティビティ Divya Gaddipati さんによって 回答されました 2019 年 10 月 22 日
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?

  0 件のコメント

サインイン to comment.

タグ

製品


リリース

R2018b

1 件の回答

回答者: Divya Gaddipati 2019 年 10 月 22 日

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.
  • In case of sequence classification, it refers to the number of classes.

  0 件のコメント

サインイン to comment.



Translated by