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.
%0 Generic
%1 chung2014empirical
%A Chung, Junyoung
%A Gulcehre, Caglar
%A Cho, KyungHyun
%A Bengio, Yoshua
%D 2014
%K final thema:dEFEND
%T Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
%U http://arxiv.org/abs/1412.3555
%X 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.
@misc{chung2014empirical,
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.},
added-at = {2021-04-16T13:37:16.000+0200},
author = {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua},
biburl = {https://www.bibsonomy.org/bibtex/24e484a5052abe2440c0e02fd1490adfa/nilsd},
interhash = {71c265fbc9bb1b77ff01e49d8f3d5387},
intrahash = {4e484a5052abe2440c0e02fd1490adfa},
keywords = {final thema:dEFEND},
note = {Presented in NIPS 2014 Deep Learning and Representation Learning Workshop},
timestamp = {2021-05-12T17:49:19.000+0200},
title = {Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling},
url = {http://arxiv.org/abs/1412.3555},
year = 2014
}