{"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/zoneout-regularizing-rnns-by-randomly","title":"Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations","arxiv_id":"1606.01305","date":"2016-06-03","proceeding":null,"authors":["David Krueger","Tegan Maharaj","János Kramár","Mohammad Pezeshki","Nicolas Ballas","Nan Rosemary Ke","Anirudh Goyal","Yoshua Bengio","Aaron Courville","Chris Pal"],"abstract":"We propose zoneout, a novel method for regularizing RNNs. At each timestep,\nzoneout stochastically forces some hidden units to maintain their previous\nvalues. Like dropout, zoneout uses random noise to train a pseudo-ensemble,\nimproving generalization. But by preserving instead of dropping hidden units,\ngradient information and state information are more readily propagated through\ntime, as in feedforward stochastic depth networks. We perform an empirical\ninvestigation of various RNN regularizers, and find that zoneout gives\nsignificant performance improvements across tasks. We achieve competitive\nresults with relatively simple models in character- and word-level language\nmodelling on the Penn Treebank and Text8 datasets, and combining with recurrent\nbatch normalization yields state-of-the-art results on permuted sequential\nMNIST.","url_abs":"http://arxiv.org/abs/1606.01305v4","url_pdf":"http://arxiv.org/pdf/1606.01305v4.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":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/teganmaharaj/zoneout","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/WelkinYang/Zoneout-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/khaleelkhan/evnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/lmnt-com/haste","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/weixsong/zoneout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/yanggeng1995/zoneout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/ZoneoutRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/MindSpore-scientific/code-13/tree/main/ZoneoutRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/MindSpore-scientific/code-8/tree/main/ZoneoutRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"zoneout-regularizing-rnns-by-randomly","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/7/ZoneoutRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"zoneout","method_name":"Zoneout"}],"datasets_introduced":[],"methods_introduced":[{"slug":"zoneout","name":"Zoneout","full_name":"Zoneout"}],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.01305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.01305"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/WelkinYang/Zoneout-Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/teganmaharaj/zoneout","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/7/ZoneoutRNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/ZoneoutRNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weixsong/zoneout","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lmnt-com/haste","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yanggeng1995/zoneout","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-13/tree/main/ZoneoutRNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-8/tree/main/ZoneoutRNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/khaleelkhan/evnn","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"c06dbbcc3bc371e5","entry":"download_and_load_datasets","repo":"weixsong/zoneout","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/weixsong/zoneout/blob/HEAD/data_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c06dbbcc3bc371e5"}},{"code_sha256_prefix":"4d467dd4b34feb3d","entry":"load_dataset","repo":"weixsong/zoneout","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/weixsong/zoneout/blob/HEAD/data_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d467dd4b34feb3d"}},{"code_sha256_prefix":"24ca10abbc4cabce","entry":"load_directory_data","repo":"weixsong/zoneout","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/weixsong/zoneout/blob/HEAD/data_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"24ca10abbc4cabce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}