{"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/towards-non-saturating-recurrent-units-for","title":"Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies","arxiv_id":"1902.06704","date":"2019-01-22","proceeding":null,"authors":["Sarath Chandar","Chinnadhurai Sankar","Eugene Vorontsov","Samira Ebrahimi Kahou","Yoshua Bengio"],"abstract":"Modelling long-term dependencies is a challenge for recurrent neural\nnetworks. This is primarily due to the fact that gradients vanish during\ntraining, as the sequence length increases. Gradients can be attenuated by\ntransition operators and are attenuated or dropped by activation functions.\nCanonical architectures like LSTM alleviate this issue by skipping information\nthrough a memory mechanism. We propose a new recurrent architecture\n(Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but\nforgoes both saturating activation functions and saturating gates, in order to\nfurther alleviate vanishing gradients. In a series of synthetic and real world\ntasks, we demonstrate that the proposed model is the only model that performs\namong the top 2 models across all tasks with and without long-term\ndependencies, when compared against a range of other architectures.","url_abs":"http://arxiv.org/abs/1902.06704v1","url_pdf":"http://arxiv.org/pdf/1902.06704v1.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":"towards-non-saturating-recurrent-units-for","repo_url":"https://github.com/apsarath/NRU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"towards-non-saturating-recurrent-units-for","repo_url":"https://github.com/Selozhd/UngatedRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"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":{"atlas_url":"https://app.syntology.ai/?focus=1902.06704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06704"}},"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/apsarath/NRU","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Selozhd/UngatedRNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1},"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":"909774cc194496f7","entry":"act_name","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/utils/utils.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/utils/utils.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":"909774cc194496f7"}},{"code_sha256_prefix":"cfe4e510a991ea63","entry":"compute_sequence_lengths","repo":"Selozhd/UngatedRNN","repo_kind":"listed","path":"tf_tools.py","file_url":"https://github.com/Selozhd/UngatedRNN/blob/HEAD/tf_tools.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":"cfe4e510a991ea63"}},{"code_sha256_prefix":"6694cfdd3a8e5d7a","entry":"cosine_similarity","repo":"Selozhd/UngatedRNN","repo_kind":"listed","path":"tf_tools.py","file_url":"https://github.com/Selozhd/UngatedRNN/blob/HEAD/tf_tools.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":"6694cfdd3a8e5d7a"}},{"code_sha256_prefix":"33a1f20d474facef","entry":"create_config","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/utils/utils.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/utils/utils.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":"33a1f20d474facef"}},{"code_sha256_prefix":"fdb63c23e69ffcc5","entry":"download_and_parse_mnist_file","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/task/load_mnist.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/task/load_mnist.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":"fdb63c23e69ffcc5"}},{"code_sha256_prefix":"cc21f73dafd45cce","entry":"download_file","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/task/load_mnist.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/task/load_mnist.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":"cc21f73dafd45cce"}},{"code_sha256_prefix":"e596020ee768543c","entry":"my_variable","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/utils/utils.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/utils/utils.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":"e596020ee768543c"}},{"code_sha256_prefix":"2f7108d6302e9487","entry":"parse_idx","repo":"apsarath/NRU","repo_kind":"official","path":"nru_project/task/load_mnist.py","file_url":"https://github.com/apsarath/NRU/blob/HEAD/nru_project/task/load_mnist.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":"2f7108d6302e9487"}},{"code_sha256_prefix":"3f581dc99da25b47","entry":"tf_matmul","repo":"Selozhd/UngatedRNN","repo_kind":"listed","path":"tf_tools.py","file_url":"https://github.com/Selozhd/UngatedRNN/blob/HEAD/tf_tools.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":"3f581dc99da25b47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}