Pith. sign in

On the compression of recurrent neural networks with an application to lvcsr acoustic modeling for embedded speech recognition,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Restricted Recurrent Neural Networks

cs.CL · 2019-08-21 · conditional · novelty 5.0

Partial sharing of input and hidden-state weights in RNN, LSTM, and GRU yields about 50% parameter reduction with roughly unchanged perplexity on two language-modeling benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Restricted Recurrent Neural Networks cs.CL · 2019-08-21 · conditional · none · ref 6

    Partial sharing of input and hidden-state weights in RNN, LSTM, and GRU yields about 50% parameter reduction with roughly unchanged perplexity on two language-modeling benchmarks.