Papers › Improving neural networks by preventing co-adaptation of feature detectors

Improving neural networks by preventing co-adaptation of feature detectors

3 Jul 2012arXiv:1207.0580archive 2025-07-28

Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random "dropout" gives big improvements on many benchmark tasks and sets new records for speech and object recognition.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

DylanMuir/fmin_adam mentioned on GitHubSyntology: not harvested report
cs20m072/DL-assignment-2-Part-B mentioned on GitHubpytorchSyntology: not harvested report
dnouri/cuda-convnet mentioned on GitHubSyntology: not harvested report
kahnchana/RNN mentioned on GitHubtorchSyntology: not harvested report
luckytiger123/dropmessage mentioned on GitHubpytorchSyntology: not harvested report
maddin79/darch mentioned on GitHubGPL-3.0Syntology: not harvested report
mdenil/dropout mentioned on GitHubMITSyntology: not harvested report
poperson1205/knowledge_distillation mentioned on GitHubpytorchSyntology: not harvested report
w510056105/DeepLearning mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Large-Scale Study on Regularization and Normalization in GANs (arXiv:1807.04720; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
xiangyu-liu/Computer-Network mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified); nothing checks that they implement this paper's method. report
zjunet/dropmessage mentioned on GitHubpytorchSyntology: not harvested 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

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

Tasks

Image ClassificationObject Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Improving neural networks by preventing co-adaptation of feature detectors Percentage correct 84.4 #237 of 265 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.

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