{"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/recurrent-batch-normalization","title":"Recurrent Batch Normalization","arxiv_id":"1603.09025","date":"2016-03-30","proceeding":null,"authors":["Tim Cooijmans","Nicolas Ballas","César Laurent","Çağlar Gülçehre","Aaron Courville"],"abstract":"We propose a reparameterization of LSTM that brings the benefits of batch\nnormalization to recurrent neural networks. Whereas previous works only apply\nbatch normalization to the input-to-hidden transformation of RNNs, we\ndemonstrate that it is both possible and beneficial to batch-normalize the\nhidden-to-hidden transition, thereby reducing internal covariate shift between\ntime steps. We evaluate our proposal on various sequential problems such as\nsequence classification, language modeling and question answering. Our\nempirical results show that our batch-normalized LSTM consistently leads to\nfaster convergence and improved generalization.","url_abs":"http://arxiv.org/abs/1603.09025v5","url_pdf":"http://arxiv.org/pdf/1603.09025v5.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":"recurrent-batch-normalization","repo_url":"https://github.com/Tetsuya-Nishikawa/ConvLSTM_DEMO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"recurrent-batch-normalization","repo_url":"https://github.com/codedecde/Recognizing-Textual-Entailment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"recurrent-batch-normalization","repo_url":"https://github.com/cooijmanstim/recurrent-batch-normalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-text8","task":"Language Modelling","dataset":"Text8","model":"BN LSTM","rank_in_archive_order":20,"of":24,"metrics":{"Bit per Character (BPC)":"1.36","Number of params":"16M"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"BN LSTM","rank_in_archive_order":22,"of":30,"metrics":{"Permuted Accuracy":"95.4%","Unpermuted Accuracy":"99%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.09025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09025"}},"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/cooijmanstim/recurrent-batch-normalization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/codedecde/Recognizing-Textual-Entailment","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Tetsuya-Nishikawa/ConvLSTM_DEMO","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"955f7f752e86fa7d","entry":"build_embedding_matrix_from_gensim","repo":"codedecde/Recognizing-Textual-Entailment","repo_kind":"listed","path":"Lang.py","file_url":"https://github.com/codedecde/Recognizing-Textual-Entailment/blob/HEAD/Lang.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"955f7f752e86fa7d"}},{"code_sha256_prefix":"51b3e8b468dbc5c2","entry":"build_vocab","repo":"codedecde/Recognizing-Textual-Entailment","repo_kind":"listed","path":"Lang.py","file_url":"https://github.com/codedecde/Recognizing-Textual-Entailment/blob/HEAD/Lang.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51b3e8b468dbc5c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}