{"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/coupled-oscillatory-recurrent-neural-network","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","arxiv_id":"2010.00951","date":"2020-10-02","proceeding":"ICLR 2021 1","authors":["T. Konstantin Rusch","Siddhartha Mishra"],"abstract":"Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state variables bounded, we propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations, modeling networks of controlled nonlinear oscillators. We prove precise bounds on the gradients of the hidden states, leading to the mitigation of the exploding and vanishing gradient problem for this RNN. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks, demonstrating the potential of this architecture to provide stable and accurate RNNs for processing complex sequential data.","url_abs":"https://arxiv.org/abs/2010.00951v2","url_pdf":"https://arxiv.org/pdf/2010.00951v2.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":"coupled-oscillatory-recurrent-neural-network","repo_url":"https://github.com/tk-rusch/coRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"coRNN","rank_in_archive_order":43,"of":49,"metrics":{"Accuracy":"87.4%"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"coRNN","rank_in_archive_order":11,"of":30,"metrics":{"Permuted Accuracy":"97.34%","Unpermuted Accuracy":"99.4%"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-noise","task":"Sequential Image Classification","dataset":"noise padded CIFAR-10","model":"coRNN","rank_in_archive_order":4,"of":7,"metrics":{"% Test Accuracy":"59.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.00951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00951"}},"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/tk-rusch/coRNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"fd308c50fdd7ff27","entry":"binary_accuracy","repo":"tk-rusch/coRNN","repo_kind":"official","path":"HAR-2/har2_task.py","file_url":"https://github.com/tk-rusch/coRNN/blob/HEAD/HAR-2/har2_task.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd308c50fdd7ff27"}},{"code_sha256_prefix":"10c7b6d241358ca5","entry":"binary_accuracy","repo":"tk-rusch/coRNN","repo_kind":"official","path":"IMDB/IMDB_task.py","file_url":"https://github.com/tk-rusch/coRNN/blob/HEAD/IMDB/IMDB_task.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":"10c7b6d241358ca5"}},{"code_sha256_prefix":"b6747f361a58a902","entry":"get_batch","repo":"tk-rusch/coRNN","repo_kind":"official","path":"adding/utils.py","file_url":"https://github.com/tk-rusch/coRNN/blob/HEAD/adding/utils.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":"b6747f361a58a902"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}