The DOI matches its Crossref record.
The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
Abstract
Recurrent nets are in principle capable to store past inputs to produce the currently desired output. Because of this property recurrent nets are used in time series prediction and process control. Practical applications involve temporal dependencies spanning many time steps, e.g. between relevant inputs and desired outputs. In this case, however, gradient based learning methods take too much time. The extremely increased learning time arises because the error vanishes as it gets propagated back. In this article the de-caying error flow is theoretically analyzed. Then methods trying to overcome vanishing gradients are briefly discussed. Finally, experiments comparing conventional algorithms and alternative methods are presented. With advanced methods long time lag problems can be solved in reasonable time.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“Moreover, by reducing the vanishing gradient problem, ReLU [92] could be utilized as a non-saturating activation function to enhance the rate of convergence [93].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [93]
In the citing paper
“Despite their capabilities in time-series-analysis tasks [116], RNNs are challenging to be trained because of the vanishing gradient problem [117] and are costly to run in terms of time and power consumption [118].”
From Brain-inspired computing systems: a systematic literature review (2024) · cites this paper as [117]
In the citing paper
“We suspect that the gate-less RNNs struggled to converge due to the vanishing gradient problem, which is a known issue with these networks in the presence of long time lags [47].”
From Emergence of belief-like representations through reinforcement learning (2023) · cites this paper as [47]
In the citing paper
“it was pointed out that BP with sigmoid activation function has the vanishing gradient problem and is thus difficult to follow deeper and more abstract training [42].”
From Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis (2018) · cites this paper as [42]
Citations
Cites
Still being checked.
Cited by
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
A survey of the recent architectures of deep convolutional neural networks
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09825-6 · Cited by 3,137
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Tai, K. S., Socher, R., & Manning, C. D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1150 · Cited by 3,081
Metadata
- Authors
- Hochreiter, S.
- Affiliations
- Technical University of Munich (DE)
- Corresponding author
- Hochreiter, Sepp
- ORCID
- Hochreiter, Sepp
- Venue
- International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
- Publisher
- World Scientific Pub Co Pte Ltd
- Published
- 1998-04
- Volume
- 06
- Issue
- 02
- Pages
- 107-116
- ISSN
- 0218-4885 (ISSN-L)
- 1793-6411
- OpenAlex
- W2069143585
- Cited by
- 2,939
- References
- 0
- Citations by year
- 2026: 130 · 2025: 291 · 2024: 381 · 2023: 365 · 2022: 453 · 2021: 375 · 2020: 349 · 2019: 223 · 2018: 150 · 2017: 98 · 2016: 63 · 2015: 25 · 2014: 7 · 2013: 8 · 2012: 5
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- International Journal of Uncertainty Fuzziness and Knowledge-Based Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Keywords
- gradient vanishing, recurrent neural networks, gradient-based learning, error propagation, temporal dependencies, time series forecasting, process control, learning time
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: The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions. https://app.cochat.ai/papers/10.1142/s0218488598000094
- The paper
- Hochreiter, S. (1998). The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. https://doi.org/10.1142/s0218488598000094
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.