{"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/the-unreasonable-effectiveness-of-the-forget","title":"The unreasonable effectiveness of the forget gate","arxiv_id":"1804.04849","date":"2018-04-13","proceeding":null,"authors":["Jos van der Westhuizen","Joan Lasenby"],"abstract":"Given the success of the gated recurrent unit, a natural question is whether\nall the gates of the long short-term memory (LSTM) network are necessary.\nPrevious research has shown that the forget gate is one of the most important\ngates in the LSTM. Here we show that a forget-gate-only version of the LSTM\nwith chrono-initialized biases, not only provides computational savings but\noutperforms the standard LSTM on multiple benchmark datasets and competes with\nsome of the best contemporary models. Our proposed network, the JANET, achieves\naccuracies of 99% and 92.5% on the MNIST and pMNIST datasets, outperforming the\nstandard LSTM which yields accuracies of 98.5% and 91%.","url_abs":"http://arxiv.org/abs/1804.04849v3","url_pdf":"http://arxiv.org/pdf/1804.04849v3.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":"the-unreasonable-effectiveness-of-the-forget","repo_url":"https://github.com/JosvanderWesthuizen/janet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.04849","atlas_url":"https://app.syntology.ai/?focus=1804.04849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04849"}},"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/JosvanderWesthuizen/janet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"97e5fde7f00efbcd","entry":"bias_initializer","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/rnn_cells.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/rnn_cells.py","link_basis":"first_harvest_node","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":"97e5fde7f00efbcd"}},{"code_sha256_prefix":"1f5d644b13f89499","entry":"calculate_metrics","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/ops.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/ops.py","link_basis":"first_harvest_node","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":"1f5d644b13f89499"}},{"code_sha256_prefix":"1978bc7747dffa0b","entry":"chrono_init","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/rnn_cells.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/rnn_cells.py","link_basis":"first_harvest_node","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":"1978bc7747dffa0b"}},{"code_sha256_prefix":"2fc4c817006d0cf1","entry":"create_conf_dict","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/ops.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/ops.py","link_basis":"first_harvest_node","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":"2fc4c817006d0cf1"}},{"code_sha256_prefix":"d73e7b76fb2fe4a4","entry":"create_scalar_summaries","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/tf_ops.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/tf_ops.py","link_basis":"first_harvest_node","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":"d73e7b76fb2fe4a4"}},{"code_sha256_prefix":"a62eef0fd59a65e3","entry":"get_add","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"prepare_data.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/prepare_data.py","link_basis":"first_harvest_node","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":"a62eef0fd59a65e3"}},{"code_sha256_prefix":"c09a3cba061368d7","entry":"get_validset_feeds","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/ops.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/ops.py","link_basis":"first_harvest_node","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":"c09a3cba061368d7"}},{"code_sha256_prefix":"cfd133b284c3f8ad","entry":"linear","repo":"JosvanderWesthuizen/janet","repo_kind":"official","path":"aux_code/tf_ops.py","file_url":"https://github.com/JosvanderWesthuizen/janet/blob/HEAD/aux_code/tf_ops.py","link_basis":"first_harvest_node","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":"cfd133b284c3f8ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}