The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Learning to Forget: Continual Prediction with LSTM
Abstract
Long short-term memory (LSTM; Hochreiter & Schmidhuber, 1997) can solve numerous tasks not solvable by previous learning algorithms for recurrent neural networks (RNNs). We identify 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 indefinitely and eventually cause the network to break down. Our remedy is a novel, adaptive “forget gate” that enables an LSTM cell to learn to reset itself at appropriate times, thus releasing internal resources. We review illustrative benchmark problems on which standard LSTM outperforms other RNN algorithms. All algorithms (including LSTM) fail to solve continual versions of these problems. LSTM with forget gates, however, easily solves them, and in an elegant way.
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.
Integrity signals
Registry
Cites
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“LSTM introduces the forget gate (Gers et al., 2000) to reset its memory state, and the forget gate is proven to be the most important component in the LSTM (van der Westhuizen and Lasenby, 2018).”
From Memformer: a memory-augmented transformer for sequence modeling (2020) · cites this paper as Gers et al., 2000
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Self-citation
Research works printed but not linked: 13
- 10.1109/72.279181 · DOI · Paper page
- 10.1162/neco.1989.1.3.372 · DOI · Paper page
- 10.1016/0893-6080(89)90022-1 · DOI
- 10.1109/72.548162 · DOI · Paper page
- Mozer M. C., 1989, Complex Systems, 3, 349
- 10.1109/72.410363 · DOI · Paper page
- 10.1080/09540098908915650 · DOI
- 10.1162/neco.1992.4.2.243 · DOI
- 10.1162/089976699300016467 · DOI
- 10.1142/S0129065789000037 · DOI
- 10.1162/neco.1989.1.1.39 · DOI · Paper page
- 10.1016/0893-6080(88)90007-X · DOI · Paper page
- 10.1162/neco.1990.2.4.490 · DOI · Paper page
Cited by
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Self-citationRecent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Reservoir computing approaches to recurrent neural network training
Lukoševičius, M., & Jaeger, H. (2009) · Computer Science Review · doi:10.1016/j.cosrev.2009.03.005 · Cited by 2,956
Long short-term memory recurrent neural network architectures for large scale acoustic modeling
Sak, H., Senior, A., & Beaufays, F. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-80 · Cited by 2,973
Metadata
- Authors
- Gers, F. A., Schmidhuber, J., & Cummins, F.
- Affiliations
- IDSIA, 6900 Lugano, Switzerland
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 2000-10-01
- Volume
- 12
- Issue
- 10
- Pages
- 2451-2471
- ISSN
- 0899-7667
- 1530-888X
- Cited by
- 4,823
- References
- 1
- Language
- en
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: Learning to Forget: Continual Prediction with LSTM. https://app.cochat.ai/papers/10.1162/089976600300015015
- The paper
- Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Computation. https://doi.org/10.1162/089976600300015015
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.
