Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. arXiv:1412.3555 [cs], December, 2014. arXiv: 1412.3555![Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex 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.
@article{chung_empirical_2014,
title = {Empirical {Evaluation} of {Gated} {Recurrent} {Neural} {Networks} on {Sequence} {Modeling}},
url = {http://arxiv.org/abs/1412.3555},
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.},
urldate = {2022-03-02},
journal = {arXiv:1412.3555 [cs]},
author = {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua},
month = dec,
year = {2014},
note = {arXiv: 1412.3555},
keywords = {Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing},
}
Downloads: 0
{"_id":"52nhFryrFJSeEqhPv","bibbaseid":"chung-gulcehre-cho-bengio-empiricalevaluationofgatedrecurrentneuralnetworksonsequencemodeling-2014","downloads":0,"creationDate":"2018-01-22T16:01:13.694Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","author_short":["Chung, J.","Gulcehre, C.","Cho, K.","Bengio, Y."],"year":2014,"bibtype":"article","biburl":"https://bibbase.org/zotero/mxmplx","bibdata":{"bibtype":"article","type":"article","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","url":"http://arxiv.org/abs/1412.3555","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.","urldate":"2022-03-02","journal":"arXiv:1412.3555 [cs]","author":[{"propositions":[],"lastnames":["Chung"],"firstnames":["Junyoung"],"suffixes":[]},{"propositions":[],"lastnames":["Gulcehre"],"firstnames":["Caglar"],"suffixes":[]},{"propositions":[],"lastnames":["Cho"],"firstnames":["KyungHyun"],"suffixes":[]},{"propositions":[],"lastnames":["Bengio"],"firstnames":["Yoshua"],"suffixes":[]}],"month":"December","year":"2014","note":"arXiv: 1412.3555","keywords":"Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing","bibtex":"@article{chung_empirical_2014,\n\ttitle = {Empirical {Evaluation} of {Gated} {Recurrent} {Neural} {Networks} on {Sequence} {Modeling}},\n\turl = {http://arxiv.org/abs/1412.3555},\n\tabstract = {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.},\n\turldate = {2022-03-02},\n\tjournal = {arXiv:1412.3555 [cs]},\n\tauthor = {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua},\n\tmonth = dec,\n\tyear = {2014},\n\tnote = {arXiv: 1412.3555},\n\tkeywords = {Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing},\n}\n\n","author_short":["Chung, J.","Gulcehre, C.","Cho, K.","Bengio, Y."],"key":"chung_empirical_2014","id":"chung_empirical_2014","bibbaseid":"chung-gulcehre-cho-bengio-empiricalevaluationofgatedrecurrentneuralnetworksonsequencemodeling-2014","role":"author","urls":{"Paper":"http://arxiv.org/abs/1412.3555"},"keyword":["Computer Science - Machine Learning","Computer Science - Neural and Evolutionary Computing"],"metadata":{"authorlinks":{}},"html":""},"search_terms":["empirical","evaluation","gated","recurrent","neural","networks","sequence","modeling","chung","gulcehre","cho","bengio"],"keywords":["computer science - machine learning","computer science - neural and evolutionary computing"],"authorIDs":[],"dataSources":["9cexBw6hrwgyZphZZ","aXmRAq63YsH7a3ufx"]}