Papers › A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

16 Dec 2015NeurIPS 2016 12arXiv:1512.05287archive 2025-07-28

Yarin Gal, Zoubin Ghahramani

Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout. This grounding of dropout in approximate Bayesian inference suggests an extension of the theoretical results, offering insights into the use of dropout with RNN models. We apply this new variational inference based dropout technique in LSTM and GRU models, assessing it on language modelling and sentiment analysis tasks. The new approach outperforms existing techniques, and to the best of our knowledge improves on the single model state-of-the-art in language modelling with the Penn Treebank (73.4 test perplexity). This extends our arsenal of variational tools in deep learning.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1512.05287")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: community (archive-listed): 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

HKUST-KnowComp/R-Net mentioned on GitHubtf report
SuperKam91/bnn mentioned on GitHubtf report
Waino/hnmt mentioned on GitHub report
abdelrahmansaud/vLSTM mentioned on GitHubpytorch report
bhaddow/dev-nematus mentioned on GitHubtf report
josephdviviano/lstm-variational-dropout mentioned on GitHubpytorch report
magahub/songrnn mentioned on GitHubtf report
martin-gorner/tensorflow-rnn-shakespeare mentioned on GitHubtfApache-2.0 report
samihadouaj/siyanWork mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
shivam13juna/Sequence_Prediction_LSTM_CHAR mentioned on GitHubtfApache-2.0 report
yaringal/BayesianRNN mentioned on GitHubMIT report
zhangyaoyuan/GAN-Simplification mentioned on GitHubtf 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

3 samples harvested; 0 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from martin-gorner/tensorflow-rnn-shakespeare. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

convert_from_alphabet martin-gorner/tensorflow-rnn-shakespeare/my_txtutils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c44c51d06ba92e6 · report
convert_to_alphabet martin-gorner/tensorflow-rnn-shakespeare/my_txtutils.py community (archive-listed) unverified Apache-2.0 (permissive) · 85e5d2ed0f8daaa1 · report
encode_text martin-gorner/tensorflow-rnn-shakespeare/my_txtutils.py community (archive-listed) unverified Apache-2.0 (permissive) · 89e3c1684fe53b8b · report

Tasks

Bayesian InferenceDeep LearningLanguage ModellingSentiment AnalysisVariational Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) Gal & Ghahramani (2016) - Variational LSTM (large) Test perplexity 75.2 #35 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Gal & Ghahramani (2016) - Variational LSTM (large) Validation perplexity 77.9 #35 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Gal & Ghahramani (2016) - Variational LSTM (medium) Test perplexity 79.7 #38 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Gal & Ghahramani (2016) - Variational LSTM (medium) Validation perplexity 81.9 #38 of 43 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Embedding Dropout, Variational Dropout

DropoutEmbedding DropoutGRULSTMSigmoid ActivationTanh ActivationVariational Dropout

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