Dissertation · 2001 · Open access
Long short-term memory in recurrent neural networks
Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Published 1 January 2001 · DOI 10.5075/epfl-thesis-2366
In brief
“Long short-term memory in recurrent neural networks” is a 2001 dissertation by Felix A. Gers, published in Infoscience (Ecole Polytechnique Fédérale de Lausanne). OpenAlex counts 257 citations as of 16 November 2026. It is open access: the full text is free to read at Infoscience (Ecole Polytechnique Fédérale de Lausanne).
- Citations
- 257
- Most cited in
- 2019 (35)
- References
- 3
- Authors
- 1
Abstract
For a long time, recurrent neural networks (RNNs) were thought to be theoretically fascinating. Unlike standard feed-forward networks RNNs can deal with arbitrary input sequences instead of static input data only. This combined with the ability to memorize relevant events over time makes recurrent networks in principal more powerful than standard feed-forward networks. The set of potential applications is enormous: any task that requires to learn how to use memory is a potential task for recurrent networks. Potential application areas include time series prediction, motor control in non-Markovian environments and rhythm detection (in music and speech). Previous successes in real world applications, with recurrent networks were limited, however, due to practical problems when long time lags between relevant events make learning dicult. For these applications conventional gradient-based recurrent network algorithms for learning to store information over extended time intervals take too long. The main reason for this failure is the rapid decay of back-propagated error. The \\Long Short Term Memory" (LSTM) algorithm overcomes this and related problems by enforcing constant error ow. Using gradient descent, LSTM explicitly learns when to store information and when to access it. In this thesis we extend, analyze, and apply the LSTM algorithm. In particular, we identify two weaknesses of LSTM, oer solutions and modify the algorithm accordingly: (1) We recognize a weakness of LSTM networks processing continual input streams that are not a priori segmented into subsequences with explicitly marked ends at which the network's internal state could be reset. Without resets, the state may grow indenitely and eventually cause the network to break down. Our remedy is a novel, adaptiv...
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Gers, F. A. (2001). Long short-term memory in recurrent neural networks. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-2366
MLA 9
Gers, Felix A. “Long short-term memory in recurrent neural networks.” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2001. https://doi.org/10.5075/epfl-thesis-2366.
Chicago
Gers, Felix A. 2001. “Long short-term memory in recurrent neural networks.” Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-2366.
Harvard
Gers, F. A. (2001) ‘Long short-term memory in recurrent neural networks’, Infoscience (Ecole Polytechnique Fédérale de Lausanne). doi:10.5075/epfl-thesis-2366.
IEEE
F. A. Gers, “Long short-term memory in recurrent neural networks,” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2001, doi: 10.5075/epfl-thesis-2366.
BibTeX
@phdthesis{gers2001long,
title = {{Long short-term memory in recurrent neural networks}},
author = {Gers, Felix A.},
year = {2001},
doi = {10.5075/epfl-thesis-2366},
url = {https://doi.org/10.5075/epfl-thesis-2366}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2016 | 21 | |
| 2017 | 24 | |
| 2018 | 26 | |
| 2019 | 35 | |
| 2020 | 33 | |
| 2021 | 26 | |
| 2022 | 19 | |
| 2023 | 20 | |
| 2024 | 11 | |
| 2025 | 5 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- long short-term memory
- recurrent neural networks
- time series forecasting
- motor control
- rhythm detection
- state reset
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Gers, F. A. (2001). Long short-term memory in recurrent neural networks. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.5075/epfl-thesis-2366
How many times has this paper been cited?
257 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Infoscience (Ecole Polytechnique Fédérale de Lausanne).
Who wrote this paper?
Felix A. Gers.
What is the DOI of this paper?
10.5075/epfl-thesis-2366. The permanent link is https://doi.org/10.5075/epfl-thesis-2366.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.