Papers › Recurrent Neural Network Regularization

Recurrent Neural Network Regularization

8 Sep 2014arXiv:1409.2329archive 2025-07-28

Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals

We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (wojzaremba/lstm) was not harvested; the 6 samples below come from 2 community repositories.

Syntology 6 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 2 repositories, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

wojzaremba/lstm officialmentioned in papermentioned on GitHubApache-2.0Syntology: not harvested report
FredericGodin/QuasiRNN-DReLU mentioned on GitHubSyntology: not harvested report
Goodideax/lstm-negtive mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
Goodideax/rnn_neg_efficient mentioned on GitHubpytorchSyntology: not harvested report
ahmetumutdurmus/zaremba mentioned on GitHubpytorchSyntology: not harvested report
dhecloud/simple_language_modelling mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
floydhub/word-language-model mentioned on GitHubpytorchSyntology: not harvested report
hikaruya8/lstm_model_py mentioned on GitHubpytorchSyntology: not harvested report
hjc18/language_modeling_lstm mentioned on GitHubpytorchSyntology: not harvested report
isi-nlp/Zoph_RNN mentioned on GitHubSyntology: not harvested report
martin-gorner/tensorflow-rnn-shakespeare mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Theoretically Grounded Application of Dropout in Recurrent Neural Networks (arXiv:1512.05287; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nbansal90/bAbi_QA mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Memory Networks (arXiv:1410.3916; that paper's own run record: 0 ran · 4 unverified) and End-To-End Memory Networks (arXiv:1503.08895; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
rgarzonj/LSTMs mentioned on GitHubtfSyntology: not harvested report
sebastianGehrmann/tensorflow-statereader mentioned on GitHubtfSyntology: not harvested report
shivam13juna/Sequence_Prediction_LSTM_CHAR mentioned on GitHubtfApache-2.0Syntology: not harvested report
simon-benigeri/lstm-language-model mentioned on GitHubpytorchSyntology: not harvested report
tmatha/lstm mentioned on GitHubtfMITSyntology: not harvested report
tomsercu/lstm mentioned on GitHubApache-2.0Syntology: not harvested report
MindSpore-scientific/code-14 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data,... (arXiv:2306.01116; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Similarity of Neural Network Models: A Survey of Functional and Representational Measures (arXiv:2305.06329; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jincan333/lot pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

6 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
4unverified

Licence: 6 of the 6 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Goodideax/lstm-negtive community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
minibatch ensemble.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 07d70b54781a432d · report fixture: signature data:ndarray/1/int, batch_size:int/0/int, seq_length:int/0/int · returned list · level recorded 2026-09-22
nll_loss in 29 papers ensemble.py ran · our draft was wrong no licence file found · pointer only · dd2e42e616936d7a · report fixture: signature scores:Tensor/2/float, y:Tensor/2/int · returned Tensor · level recorded 2026-09-22
perplexity in 22 papers ensemble.py unverified no licence file found · pointer only · d8b96d7fec1ed277 · report
dhecloud/simple_language_modelling community (archive-listed) 3 samples, 0 ran · 3 unverified
create_ptb_loader train_lm.py unverified no licence file found · pointer only · 773bac171b472d67 · report
eval in 90 papers train_lm.py unverified no licence file found · pointer only · 463f26abb478a418 · report
train in 522 papers train_lm.py unverified no licence file found · pointer only · eae89d8a906f77fb · report

Tasks

Caption GenerationImage CaptioningLanguage ModelingLanguage ModellingMachine TranslationSpeech RecognitionTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Word Level) Zaremba et al. (2014) - LSTM (large) Test perplexity 78.4 #36 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Zaremba et al. (2014) - LSTM (large) Validation perplexity 82.2 #36 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Zaremba et al. (2014) - LSTM (medium) Test perplexity 82.7 #39 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Zaremba et al. (2014) - LSTM (medium) Validation perplexity 86.2 #39 of 43 Archive leaderboard report
Machine Translation WMT2014 English-French Regularized LSTM BLEU score 29.03 #51 of 57 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

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