Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 5,591

The DOI matches its Crossref record; 109 of the 109 references it cites were found in a registry or an index.

A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

Yu, Yong, Si, Xiaosheng, Hu, Changhua, Zhang, Jianxun · 2019 · Neural Computation

Abstract

Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/neco_a_01199

Cites

109 of 109 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 41

  1. Achanta R., 2010, SLIC superpixels
  2. 10.1109/ITSC.2017.8317913 · DOI
  3. Brown B., 2004, Circuits, Signals, and Systems: IASTED International Conference Proceedings
  4. 10.1109/ICNN.1996.549199 · doi:10.1109/icnn.1996.549199
  5. Cheng M., 2016, Proceedings of the IEEE 24th International Conference on Network Protocols
  6. Deng L., 2013, APSIPA transactions on signal and information processing
  7. Francesconi E., 1997, Proceedings of the International Workshop on Graphics Recognition, 104
  8. 10.1109/CEC.2005.1555002 · doi:10.1109/cec.2005.1555002
  9. Gers F. A., 2002, Journal of Machine Learning Research, 3, 115
  10. Goller C., 1996, Neural Networks, 1, 347
  11. Guo Y., 2017, International Journal of Multimedia Information Retrieval, 2, 1
  12. Hochreiter S., 1991, Untersuchungen zu dynamischen neuronalen Netzen
  13. Hsu W. N., 2016, Cell, 50, 395
  14. Jing L., 2017, Gated orthogonal recurrent units: On learning to forget
  15. Jozefowicz R., 2015, Proceedings of the International Conference on International Conference on Machine Learning, 2342
  16. Krause B., 2016, Multiplicative LSTM for sequence modelling
  17. 10.1145/2820783.2820801 · doi:10.1145/2820783.2820801
  18. Li J., 2016, Proceedings of the Conference on Automatic Speech Recognition and Understanding, 187
  19. Mallinar N., 2018, Deep canonically correlated LSTMs
  20. McCarter G., 2007, Air freight image segmentation database
  21. Moniz J. R. A., 2018, Nested LSTMs
  22. Nair V., 2010, Proceedings of the International Conference on International Conference on Machine Learning, 807
  23. Neil D., 2016, Advances in neural information processing systems, 16, 3882
  24. Nina O., 2016, Proceedings of the International Conference on Information, Communications and Signal Processing, 1
  25. Rahman L., 2017, Proceedings of the International Conference on Electrical Engineering and Information Communication Technology, 1
  26. Ranzato M. A., 2014, Video (language) modeling: A baseline for generative models of natural videos
  27. Robinson A. J., 1987, The utility driven dynamic error propagation network
  28. Saleh K., 2018, Proceedings of the IEEE International Conference on Intelligent Transportation Systems, 327
  29. Schlag I., 2017, NIPS Metalearning Workshop
  30. Shabanian S., 2017, Variational Bi-LSTMs
  31. Shi X., 2015, Advances in neural information processing systems, 802
  32. Sutskever I., 2014, Advances in neural information processing systems, 3104
  33. Tai K. S., 2015, Computer Science, 5, 36
  34. Weng J. J., 1993, Proceedings of the Fourth International Conference on Computer Vision, 121
  35. Williams R. J., 1989, Complexity of exact gradient computation algorithms for recurrent neural networks
  36. Wu H., 2016, An empirical exploration of skip connections for sequential tagging
  37. Yao K., 2015, Depth-gated LSTM
  38. 10.1109/DSC.2018.00019 · doi:10.1109/dsc.2018.00019
  39. Zaremba W., 2014, Learning to execute
  40. Zhang J., 2016, Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing, 1655
  41. Zhou C., 2016, Computer Science, 1, 39

Cited by

See all 5,591

Metadata

Authors
Yu, Y., Si, X., Hu, C., & Zhang, J.
Venue
Neural Computation
Publisher
MIT Press
Published
2019-07
Volume
31
Issue
7
Pages
1235-1270
ISSN
  • 0899-7667 (ISSN-L)
  • 1530-888X
OpenAlex
W2944851425
Cited by
5,591
References
109
FWCI
111.78
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.