Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Code

• github.com/jych/librnn
  OfficialIn papernone★ 0
• github.com/pushpendughosh/Stock-market-forecasting
  tf★ 532
• github.com/proroklab/popgym
  pytorch★ 213
• github.com/rvandewater/yaib
  pytorch★ 94
• github.com/ratschlab/HIRID-ICU-Benchmark
  pytorch★ 60
• github.com/hkust-knowcomp/sessioncqa
  pytorch★ 3
• github.com/max-ng/GRU-recurrent-network
  none★ 0
• github.com/lugq1990/neural-nets
  tf★ 0
• github.com/abhaskumarsinha/GRU-varients
  tf★ 0
• github.com/moon23k/RNN_Seq2Seq
  pytorch★ 0

Abstract

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.

Tasks

Benchmark Results

Reproductions