Paper
Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies
ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz
In brief
“Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies” is a paper by Sepp Hochreiter and 5 co-authors, published in ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz. OpenAlex counts 887 citations as of 16 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.
- Citations
- 887
- Most cited in
- 2020 (141)
- Authors
- 6
Abstract
Introduction Recurrent networks (crossreference Chapter 12) can, in principle, use their feedback connections to store representations of recent input events in the form of activations. The most widely used algorithms for learning what to put in short-term memory, however, take too much time to be feasible or do not work well at all, especially when… Read the full abstract at the publisher.
Excerpt. This paper is not open access.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hochreiter, S., Bengio, Y., Informatik, F. F., Bengio, Y., Frasconi, P., & Schmidhuber, J. (n.d.). Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies. ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321
MLA 9
Hochreiter, Sepp, et al. “Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies.” ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz, n.d.. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321.
Chicago
Hochreiter, Sepp, Yoshua Bengio, Fakultit F/jr Informatik, Yoshua Bengio, Paolo Frasconi, and Jfirgen Schmidhuber. n.d.. “Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies.” ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321.
Harvard
Hochreiter, S. et al. (n.d.) ‘Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies’, ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz. Available at: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321.
IEEE
S. Hochreiter, Y. Bengio, F. F. Informatik, Y. Bengio, P. Frasconi, and J. Schmidhuber, “Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies,” ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz, n.d..
BibTeX
@article{hochreitergradient,
title = {{Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies}},
author = {Hochreiter, Sepp and Bengio, Yoshua and Informatik, Fakultit F/jr and Bengio, Yoshua and Frasconi, Paolo and Schmidhuber, Jfirgen},
journal = {ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 59 | |
| 2018 | 79 | |
| 2019 | 138 | |
| 2020 | 141 | |
| 2021 | 107 | |
| 2022 | 69 | |
| 2023 | 63 | |
| 2024 | 41 | |
| 2025 | 29 | |
| 2026 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- recurrent neural networks
- gradient flow
- long-range dependencies
- short-term memory
- backpropagation through time
- real-time recurrent learning
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?
Hochreiter, S., Bengio, Y., Informatik, F. F., Bengio, Y., Frasconi, P., & Schmidhuber, J. (n.d.). Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies. ftp://ftp.idsia.ch/pub/juergen/ch7.ps.gz. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7321
How many times has this paper been cited?
887 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?
OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.
Who wrote this paper?
Sepp Hochreiter, Yoshua Bengio, Fakultit F/jr Informatik, Yoshua Bengio, Paolo Frasconi, Jfirgen Schmidhuber.
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.