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

The DOI matches its Crossref record; 18 of the 18 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
DOI 10.1162/neco_a_01199
Open this paper in CoChat — free account

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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1162/neco_a_01199

Cites

18 of 18 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Show all 18 references

Research works printed but not linked: 120

  1. Achanta R., 2010, SLIC superpixels
  2. 10.1109/ITSC.2017.8317913 · DOI
  3. 10.1561/2200000006 · DOI · Paper page
  4. 10.1109/72.279181 · DOI · Paper page
  5. Britz D., 2017, Massive exploration of neural machine translation architectures
  6. Brown B., 2004, Circuits, Signals, and Systems: IASTED International Conference Proceedings
  7. 10.1155/2017/3296874 · DOI · Paper page
  8. 10.1109/ICNN.1996.549199 · doi:10.1109/icnn.1996.549199
  9. Cheng M., 2016, Proceedings of the IEEE 24th International Conference on Network Protocols
  10. Deng L., 2013, APSIPA transactions on signal and information processing
  11. 10.1109/MWSCAS.2017.8053243 · DOI · Paper page
  12. 10.1109/VTCFall.2017.8288312 · DOI
  13. 10.1207/s15516709cog1402_1 · DOI · Paper page
  14. Fernández S., 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence
  15. 10.1007/978-3-540-74695-9_23 · DOI · Paper page
  16. Francesconi E., 1997, Proceedings of the International Workshop on Graphics Recognition, 104
  17. 10.1109/72.712151 · DOI · Paper page
  18. 10.1109/CEC.2005.1555002 · doi:10.1109/cec.2005.1555002
  19. Gers F., 2001, Long short-term memory in recurrent neural networks
  20. 10.1109/IJCNN.2000.861302 · DOI · Paper page
  21. 10.1109/72.963769 · DOI · Paper page
  22. 10.1162/089976600300015015 · DOI · Paper page
  23. Gers F. A., 2002, Journal of Machine Learning Research, 3, 115
  24. 10.1007/978-3-319-11179-7_28 · DOI
  25. Goller C., 1996, Neural Networks, 1, 347
  26. 10.1007/978-3-642-24797-2 · DOI · Paper page
  27. Graves A., 2014, Generating sequences with recurrent neural networks
  28. 10.1016/j.neunet.2005.06.042 · DOI · Paper page
  29. Guo Y., 2017, International Journal of Multimedia Information Retrieval, 2, 1
  30. 10.1145/3123266.3123394 · DOI · Paper page
  31. 10.1109/ICASSP.2016.7472718 · DOI
  32. 10.1109/MWSCAS.2017.8053242 · DOI
  33. Hochreiter S., 1991, Untersuchungen zu dynamischen neuronalen Netzen
  34. Hsu W. N., 2016, Cell, 50, 395
  35. 10.21437/Interspeech.2016-491 · DOI
  36. 10.1109/TSMC.1971.4308320 · DOI · Paper page
  37. Ivakhnenko A. G., 1965, Cybernetic predicting devices
  38. Jing L., 2017, Gated orthogonal recurrent units: On learning to forget
  39. Jordan M., 1986, Proceedings of the Annual Conference of the Cognitive Science Society, 531
  40. Jozefowicz R., 2015, Proceedings of the International Conference on International Conference on Machine Learning, 2342
  41. Kalchbrenner N., 2015, Grid long short-term memory
  42. 10.1016/j.ymssp.2017.11.024 · DOI · Paper page
  43. Kim J., 2017, Residual LSTM: Design of a deep recurrent architecture for distant speech recognition
  44. Koutnik J., 2014, A clockwork RNN
  45. Krause B., 2016, Multiplicative LSTM for sequence modelling
  46. 10.1145/2820783.2820801 · doi:10.1145/2820783.2820801
  47. 10.21437/Interspeech.2017-1164 · DOI · Paper page
  48. Li J., 2015, When are tree structures necessary for deep learning of representations
  49. 10.1109/ICASSP.2016.7472617 · DOI
  50. Li J., 2016, Proceedings of the Conference on Automatic Speech Recognition and Understanding, 187
  51. 10.1109/CVPR.2017.234 · DOI
  52. 10.1109/TPAMI.2015.2408360 · DOI · Paper page
  53. 10.1007/978-3-319-46448-0_8 · DOI · Paper page
  54. 10.1109/CVPR.2016.347 · DOI · Paper page
  55. 10.1007/978-3-319-10602-1_48 · DOI · Paper page
  56. Lipton Z. C., 2015, A critical review of recurrent neural networks for sequence learning
  57. 10.18653/v1/P16-1098 · DOI
  58. Liu P., 2016, Modelling interaction of sentence pair with coupled-LSTMs
  59. 10.3390/rs9121330 · DOI · Paper page
  60. Mallinar N., 2018, Deep canonically correlated LSTMs
  61. McCarter G., 2007, Air freight image segmentation database
  62. Miwa M., 2016, End-to-end relation extraction using LSTMs on sequences and tree structures
  63. Moniz J. R. A., 2018, Nested LSTMs
  64. Mozer M. C., 1993, Advances in neural information processing systems, 5, 863
  65. Nair V., 2010, Proceedings of the International Conference on International Conference on Machine Learning, 807
  66. Neil D., 2016, Advances in neural information processing systems, 16, 3882
  67. 10.1109/DSC.2016.72 · DOI
  68. Nina O., 2016, Proceedings of the International Conference on Information, Communications and Signal Processing, 1
  69. 10.1109/ICCV.2017.208 · DOI · Paper page
  70. Oord A. V. D., 2016, Pixel recurrent neural networks
  71. 10.1109/TASLP.2016.2520371 · DOI · Paper page
  72. 10.1162/neco.1989.1.2.263 · DOI · Paper page
  73. Peng Z., 2016, Proceedings of the International Joint Conference on Artificial Intelligence, 3439
  74. 10.1007/s11263-016-0965-7 · DOI · Paper page
  75. 10.1109/IJCNN.2017.7965940 · DOI
  76. 10.1109/ASRU.2017.8268932 · DOI
  77. Rahman L., 2017, Proceedings of the International Conference on Electrical Engineering and Information Communication Technology, 1
  78. Ranzato M. A., 2014, Video (language) modeling: A baseline for generative models of natural videos
  79. Robinson A. J., 1987, The utility driven dynamic error propagation network
  80. Sak H. I., 2014, Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition
  81. Saleh K., 2018, Proceedings of the IEEE International Conference on Intelligent Transportation Systems, 327
  82. Schlag I., 2017, NIPS Metalearning Workshop
  83. Schmidhuber J., 2012, Self-delimiting neural networks
  84. 10.1162/neco.2007.19.3.757 · DOI · Paper page
  85. 10.1007/978-3-642-40602-7_18 · DOI · Paper page
  86. Shabanian S., 2017, Variational Bi-LSTMs
  87. 10.1109/ICCCNT.2017.8203938 · DOI
  88. Shi X., 2015, Advances in neural information processing systems, 802
  89. 10.1007/s41095-016-0059-z · DOI
  90. 10.1109/72.572108 · DOI · Paper page
  91. Srivastava R. K., 2015, Highway networks
  92. 10.1007/s11063-012-9259-4 · DOI
  93. Sun G., 1990, Proceedings of the International Joint Conference on Neural Networks, 577
  94. Sutskever I., 2014, Advances in neural information processing systems, 3104
  95. Tai K. S., 2015, Computer Science, 5, 36
  96. Teng Z., 2016, Bidirectional tree-structured LSTM with head lexicalization
  97. 10.1109/tcbb.2007.1015 · DOI
  98. 10.1109/ICCV.2015.460 · DOI · Paper page
  99. 10.1109/DSAA.2015.7344820 · DOI
  100. 10.1109/CVPR.2015.7298788 · DOI
  101. 10.1145/3184558.3191571 · DOI
  102. Weiss G., 2018, On the practical computational power of finite precision RNNs for language recognition
  103. Weng J. J., 1993, Proceedings of the Fourth International Conference on Computer Vision, 121
  104. 10.1016/0893-6080(88)90007-X · DOI · Paper page
  105. Williams R. J., 1989, Complexity of exact gradient computation algorithms for recurrent neural networks
  106. Wu H., 2016, An empirical exploration of skip connections for sequential tagging
  107. 10.12677/CSA.2018.81008 · DOI
  108. 10.1109/CVPR.2012.6248101 · DOI · Paper page
  109. Yang Y., 2017, IEEE Geoscience and Remote Sensing Letters, 99, 1
  110. Yao K., 2015, Depth-gated LSTM
  111. 10.1109/DSC.2018.00019 · doi:10.1109/dsc.2018.00019
  112. Zaremba W., 2014, Learning to execute
  113. Zhang J., 2016, Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing, 1655
  114. Zhang X., 2015, Tree recurrent neural networks with application to language modeling
  115. Zhang Y., 2015, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 5755
  116. 10.1109/ICSensT.2016.7796266 · DOI · Paper page
  117. Zhou C., 2016, Computer Science, 1, 39
  118. 10.1007/s11633-016-1006-2 · DOI · Paper page
  119. 10.1109/ACCESS.2017.2684186 · DOI · Paper page
  120. Zhu X., 2015, Long short-term memory over tree structures

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
DOI
10.1162/neco_a_01199
OpenAlex
W2944851425
Cited by
5,591
References
18
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. https://app.cochat.ai/papers/10.1162/neco_a_01199
The paper
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019). A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. Neural Computation. https://doi.org/10.1162/neco_a_01199

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.