The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
LSTM: A Search Space Odyssey
Open accessAbstract
Several variants of the long short-term memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful functional ANalysis Of VAriance framework. In total, we summarize the results of 5400 experimental runs ( ≈ 15 years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
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
“NLP FL is applied in next-word prediction in mobile keyboards by adopting the FedAvg algorithm to learn CIFG [93].[28,[94][95][96][97]”
From Applications of Federated Learning; Taxonomy, Challenges, and Research Trends (2022) · cites this paper as [93]
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-citationLearning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893
(2012) · Cited by 8,009
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Graves, A., & Schmidhuber, J. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.06.042 · Cited by 6,152
Self-citationGraves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Self-citationLong-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
(2013) · Cited by 3,740
Research works printed but not linked: 2
- gers, 2002, DEKF-LSTM, Proc European Symp Artificial Neural Networks (ESANN), 369
- robinson, 1987, The utility driven dynamic error propagation network
Cited by
Sorted by citations
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
Sherstinsky, A. (2020) · Physica D: Nonlinear Phenomena · doi:10.1016/j.physd.2019.132306 · Cited by 5,680
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
Yu, Y., Si, X., Hu, C., & Zhang, J. (2019) · Neural Computation · doi:10.1162/neco_a_01199 · Cited by 5,870
Character-level Convolutional Networks for Text ClassificationPreprint
Zhang, X., Zhao, J., & LeCun, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.01626 · Cited by 4,481
A review on the long short-term memory model
Houdt, G. V., Mosquera, C., & Nápoles, G. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09838-1 · Cited by 2,198
Koroniotis, N., Moustafa, N., Sitnikova, E., & Turnbull, B. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.05.041 · Cited by 1,983
Metadata
- Authors
- Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J.
- Affiliations
- University of Applied Sciences and Arts of Southern Switzerland (CH)
- ORCID
- Greff, Klaus
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2017-10
- Volume
- 28
- Issue
- 10
- Pages
- 2222-2232
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W1689711448
- Cited by
- 6,955
- References
- 53
- Citations by year
- 2026: 602 · 2025: 812 · 2024: 810 · 2023: 822 · 2022: 872 · 2021: 881 · 2020: 778 · 2019: 686 · 2018: 383 · 2017: 188
- FWCI
- 370.42
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Swiss National Science Foundation through the Project Theory and Practice of Reinforcement Learning 2, and through the Project Advanced Reinforcement Learning (138219, 156682)
- European Institute of Innovation and Technology through the Project Neural Dynamics, through the Project NASCENCE and through the Project WAY (FP7-ICT-270247, FP7-ICT-317662, FP7-ICT-288551)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- long short-term memory, recurrent neural networks, hyperparameter optimization, random search, functional analysis of variance, forget gate, speech recognition, handwriting recognition
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
