Preprint · 2014 · Open access

Learning Longer Memory in Recurrent Neural Networks

Tomáš Mikolov, Armand Joulin, Sumit Chopra, Michaël Mathieu, Marc’Aurelio Ranzato

arXiv (Cornell University) · Published 24 December 2014 · DOI 10.48550/arxiv.1412.7753

Free PDFView at the publisherCite this paper

In brief

“Learning Longer Memory in Recurrent Neural Networks” is a 2014 preprint by Tomáš Mikolov and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 288 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
288
Most cited in
2018 (37)
References
29
Authors
5

Abstract

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this paper, we show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. We encourage some of the hidden units to change their state slowly by making part of the recurrent weight matrix close to identity, thus forming kind of a longer term memory. We evaluate our model in language modeling experiments, where we obtain similar performance to the much more complex Long Short Term Memory (LSTM) networks (Hochreiter & Schmidhuber, 1997).

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Mikolov, T., Joulin, A., Chopra, S., Mathieu, M., & Ranzato, M. (2014). Learning Longer Memory in Recurrent Neural Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1412.7753

MLA 9

Mikolov, Tomáš, et al. “Learning Longer Memory in Recurrent Neural Networks.” arXiv (Cornell University), 2014. https://doi.org/10.48550/arxiv.1412.7753.

Chicago

Mikolov, Tomáš, Armand Joulin, Sumit Chopra, Michaël Mathieu, and Marc’Aurelio Ranzato. 2014. “Learning Longer Memory in Recurrent Neural Networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1412.7753.

Harvard

Mikolov, T. et al. (2014) ‘Learning Longer Memory in Recurrent Neural Networks’, arXiv (Cornell University). doi:10.48550/arxiv.1412.7753.

IEEE

T. Mikolov, A. Joulin, S. Chopra, M. Mathieu, and M. Ranzato, “Learning Longer Memory in Recurrent Neural Networks,” arXiv (Cornell University), 2014, doi: 10.48550/arxiv.1412.7753.

BibTeX

@misc{mikolov2014learning,
  title     = {{Learning Longer Memory in Recurrent Neural Networks}},
  author    = {Mikolov, Tomáš and Joulin, Armand and Chopra, Sumit and Mathieu, Michaël and Ranzato, Marc’Aurelio},
  howpublished = {arXiv (Cornell University)},
  year      = {2014},
  doi       = {10.48550/arxiv.1412.7753},
  url       = {https://doi.org/10.48550/arxiv.1412.7753}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20173030
20183737
20193333
20202727
20213333
20221313
20232121
20242424
20252121
202644

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications

  • recurrent neural networks
  • long-term memory
  • gradient vanishing
  • gradient descent learning
  • identity matrix
  • language modeling
  • natural language processing
  • LSTM comparison

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Mikolov, T., Joulin, A., Chopra, S., Mathieu, M., & Ranzato, M. (2014). Learning Longer Memory in Recurrent Neural Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1412.7753

How many times has this paper been cited?

288 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 arXiv (Cornell University).

Who wrote this paper?

Tomáš Mikolov, Armand Joulin, Sumit Chopra, Michaël Mathieu, Marc’Aurelio Ranzato.

What is the DOI of this paper?

10.48550/arxiv.1412.7753. The permanent link is https://doi.org/10.48550/arxiv.1412.7753.

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.