Multiplicative LSTM for sequence modelling

@article{Krause2016MultiplicativeLF,
  title={Multiplicative LSTM for sequence modelling},
  author={Ben Krause and Liang Lu and Iain Murray and Steve Renals},
  journal={CoRR},
  year={2016},
  volume={abs/1609.07959}
}
We introduce multiplicative LSTM (mLSTM), a novel recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition functions for each possible input, which we argue makes it more expressive for autoregressive density estimation. We demonstrate empirically that mLSTM outperforms standard LSTM and its deep variants for… CONTINUE READING
Highly Cited
This paper has 53 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 40 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 38 extracted citations

54 Citations

0204020172018
Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…