{"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/adaptive-saturated-rnn-remember-more-with-1","title":"Adaptive-saturated RNN: Remember more with less instability","arxiv_id":"2304.11790","date":"2023-04-24","proceeding":"ICLR 2023 Tiny Paper Track 2023 5","authors":["Khoi Minh Nguyen-Duy","Quang Pham","Binh T. Nguyen"],"abstract":"Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs). With orthogonal parameters and non-saturated activation functions, gradients in such models are constrained to unit norms. On the other hand, although the traditional vanilla RNNs are seen to have higher memory capacity, they suffer from the VGP and perform badly in many applications. This work proposes Adaptive-Saturated RNNs (asRNN), a variant that dynamically adjusts its saturation level between the two mentioned approaches. Consequently, asRNN enjoys both the capacity of a vanilla RNN and the training stability of orthogonal RNNs. Our experiments show encouraging results of asRNN on challenging sequence learning benchmarks compared to several strong competitors. The research code is accessible at https://github.com/ndminhkhoi46/asRNN/.","url_abs":"https://arxiv.org/abs/2304.11790v1","url_pdf":"https://arxiv.org/pdf/2304.11790v1.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":"adaptive-saturated-rnn-remember-more-with-1","repo_url":"https://github.com/ndminhkhoi46/asRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"Adaptive-saturated RNN","rank_in_archive_order":15,"of":30,"metrics":{"Permuted Accuracy":"96.96%","Unpermuted Accuracy":"99.3%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.11790","atlas_url":"https://app.syntology.ai/?focus=2304.11790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11790"}},"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":"deterministic:regex_extraction","url":"https://github.com/ndminhkhoi46/asRNN","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"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":3,"samples":[{"code_sha256_prefix":"0a29498a914df308","entry":"Orthogonal","repo":"ndminhkhoi46/asRNN","repo_kind":"official","path":"sources/custom_modules.py","file_url":"https://github.com/ndminhkhoi46/asRNN/blob/HEAD/sources/custom_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a29498a914df308"}},{"code_sha256_prefix":"3f88559752f44c0f","entry":"Parametrization","repo":"ndminhkhoi46/asRNN","repo_kind":"official","path":"sources/custom_modules.py","file_url":"https://github.com/ndminhkhoi46/asRNN/blob/HEAD/sources/custom_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f88559752f44c0f"}},{"code_sha256_prefix":"c562f5ee8406c2bd","entry":"asRNN","repo":"ndminhkhoi46/asRNN","repo_kind":"official","path":"sources/custom_modules.py","file_url":"https://github.com/ndminhkhoi46/asRNN/blob/HEAD/sources/custom_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c562f5ee8406c2bd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}