Papers › LSTM: A Search Space Odyssey

LSTM: A Search Space Odyssey

13 Mar 2015arXiv:1503.04069archive 2025-07-28

Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber

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 fANOVA 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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

17 repositories listed; official and paper-mentioned ones first.

a-martyn/unet mentioned on GitHubtf report
alexandrujeman/dqn mentioned on GitHubpytorch report
alexjeman/dqn mentioned on GitHubpytorch report
disooqi/DNN mentioned on GitHubNOASSERTION report
disooqi/Natasy mentioned on GitHubNOASSERTION report
flukeskywalker/highway-networks mentioned on GitHubNOASSERTION report
hadi-gharibi/pytorch-lstm mentioned on GitHubpytorch report
kevin28520/RNN mentioned on GitHub report
sw-scot/foco-mlmis mentioned on GitHub report
tmatha/lstm mentioned on GitHubtfMIT report
widmi/widis-lstm-tools mentioned on GitHubpytorchGPL-3.0 report
cui0523/Code6 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Handwriting RecognitionMusic ModelingSpeech Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections