{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dropout-as-a-bayesian-approximation","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","arxiv_id":"1506.02142","date":"2015-06-06","proceeding":null,"authors":["Yarin Gal","Zoubin Ghahramani"],"abstract":"Deep learning tools have gained tremendous attention in applied machine\nlearning. However such tools for regression and classification do not capture\nmodel uncertainty. In comparison, Bayesian models offer a mathematically\ngrounded framework to reason about model uncertainty, but usually come with a\nprohibitive computational cost. In this paper we develop a new theoretical\nframework casting dropout training in deep neural networks (NNs) as approximate\nBayesian inference in deep Gaussian processes. A direct result of this theory\ngives us tools to model uncertainty with dropout NNs -- extracting information\nfrom existing models that has been thrown away so far. This mitigates the\nproblem of representing uncertainty in deep learning without sacrificing either\ncomputational complexity or test accuracy. We perform an extensive study of the\nproperties of dropout's uncertainty. Various network architectures and\nnon-linearities are assessed on tasks of regression and classification, using\nMNIST as an example. We show a considerable improvement in predictive\nlog-likelihood and RMSE compared to existing state-of-the-art methods, and\nfinish by using dropout's uncertainty in deep reinforcement learning.","url_abs":"http://arxiv.org/abs/1506.02142v6","url_pdf":"http://arxiv.org/pdf/1506.02142v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/Eungyu-Jin/Dropout_uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/MIC-DKFZ/TractSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/agnesdeng/misle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/aredier/monte_carlo_dropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/arneschmidt/bayesian_deep_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/arodriguezca/uncertainty-ts-forecasting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/asharakeh/probdet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/aurelio-amerio/concretedropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/blacKitten13/Dropout-for-Model-Uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/cdebeunne/uncertainties_CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/cpark321/uncertainty-deep-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/erickgalinkin/dropout_privacy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/gtegner/hyper-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/huyng/incertae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/jelleman8/TractSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/kenya-sk/mc_dropout_tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/kosyoshida/simple-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/marcovirgolin/UncertaintyEstimationInDeepNets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/mrahtz/learning-from-human-preferences","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/omacshane/basicbayesDL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/rsilveira79/intents_uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/stat-ml/dpp-dropout-uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/statsu1990/regression_dropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/tennisonliu/bayesian-neural-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/ucl-exoplanets/ADC2023-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/Mind23-2/MindCode-152","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/mvaldenegro/keras-uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"dropout-as-a-bayesian-approximation","repo_url":"https://github.com/yaringal/DropoutUncertaintyExps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"monte-carlo-dropout","method_name":"Monte Carlo Dropout"}],"datasets_introduced":[],"methods_introduced":[{"slug":"monte-carlo-dropout","name":"Monte Carlo Dropout","full_name":"Monte Carlo Dropout"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.02142","atlas_url":"https://app.syntology.ai/?focus=1506.02142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02142"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaringal/DropoutUncertaintyExps","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asharakeh/probdet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cdebeunne/uncertainties_CNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucl-exoplanets/ADC2023-baseline","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/erickgalinkin/dropout_privacy","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/blacKitten13/Dropout-for-Model-Uncertainty","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/agnesdeng/misle","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kenya-sk/mc_dropout_tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stat-ml/dpp-dropout-uncertainty","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-152","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MIC-DKFZ/TractSeg","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mvaldenegro/keras-uncertainty","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marcovirgolin/UncertaintyEstimationInDeepNets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aredier/monte_carlo_dropout","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/omacshane/basicbayesDL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/statsu1990/regression_dropout","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gtegner/hyper-gan","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Eungyu-Jin/Dropout_uncertainty","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tennisonliu/bayesian-neural-network","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arneschmidt/bayesian_deep_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arodriguezca/uncertainty-ts-forecasting","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mrahtz/learning-from-human-preferences","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kosyoshida/simple-keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rsilveira79/intents_uncertainty","reach":{"status":"ok"}}],"summary":{"ran_violates":2,"ran_fixture":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"9dc92202a028ac23","entry":"f","repo":"arneschmidt/bayesian_deep_learning","repo_kind":"listed","path":"regression_with_GP.py","file_url":"https://github.com/arneschmidt/bayesian_deep_learning/blob/HEAD/regression_with_GP.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9dc92202a028ac23"}},{"code_sha256_prefix":"1dd2001e70f05aff","entry":"k","repo":"arneschmidt/bayesian_deep_learning","repo_kind":"listed","path":"regression_with_BNN.py","file_url":"https://github.com/arneschmidt/bayesian_deep_learning/blob/HEAD/regression_with_BNN.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1dd2001e70f05aff"}},{"code_sha256_prefix":"d853188e0b72364e","entry":"k_se","repo":"arneschmidt/bayesian_deep_learning","repo_kind":"listed","path":"regression_with_GP.py","file_url":"https://github.com/arneschmidt/bayesian_deep_learning/blob/HEAD/regression_with_GP.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d853188e0b72364e"}},{"code_sha256_prefix":"3416eab71cd2de41","entry":"mc_dropout_prediction","repo":"kenya-sk/mc_dropout_tensorflow","repo_kind":"listed","path":"src/mc_dropout_prediction.py","file_url":"https://github.com/kenya-sk/mc_dropout_tensorflow/blob/HEAD/src/mc_dropout_prediction.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3416eab71cd2de41"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}