{"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/long-expressive-memory-for-sequence-modeling-1","title":"Long Expressive Memory for Sequence Modeling","arxiv_id":"2110.04744","date":"2021-10-10","proceeding":"ICLR 2022 4","authors":["T. Konstantin Rusch","Siddhartha Mishra","N. Benjamin Erichson","Michael W. Mahoney"],"abstract":"We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies. LEM is gradient-based, it can efficiently process sequential tasks with very long-term dependencies, and it is sufficiently expressive to be able to learn complicated input-output maps. To derive LEM, we consider a system of multiscale ordinary differential equations, as well as a suitable time-discretization of this system. For LEM, we derive rigorous bounds to show the mitigation of the exploding and vanishing gradients problem, a well-known challenge for gradient-based recurrent sequential learning methods. We also prove that LEM can approximate a large class of dynamical systems to high accuracy. Our empirical results, ranging from image and time-series classification through dynamical systems prediction to speech recognition and language modeling, demonstrate that LEM outperforms state-of-the-art recurrent neural networks, gated recurrent units, and long short-term memory models.","url_abs":"https://arxiv.org/abs/2110.04744v2","url_pdf":"https://arxiv.org/pdf/2110.04744v2.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":"long-expressive-memory-for-sequence-modeling-1","repo_url":"https://github.com/tk-rusch/lem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sequential-image-classification","task_name":"Sequential Image Classification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"LEM","rank_in_archive_order":18,"of":30,"metrics":{"Permuted Accuracy":"96.6%","Unpermuted Accuracy":"99.5%"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-image-classification-on-noise","task":"Sequential Image Classification","dataset":"noise padded CIFAR-10","model":"LEM","rank_in_archive_order":3,"of":7,"metrics":{"% Test Accuracy":"60.5"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-eigenworms","task":"Time Series Classification","dataset":"EigenWorms","model":"LEM","rank_in_archive_order":1,"of":8,"metrics":{"% Test Accuracy":"92.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04744"}},"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":"deterministic:regex_extraction","url":"https://github.com/tk-rusch/LEM","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/deepmind/lamb","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tk-rusch/lem","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"found_in_text":{"samples":9,"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":1,"samples":[{"code_sha256_prefix":"9cfb904b319e5586","entry":"LEMCell","repo":"tk-rusch/lem","repo_kind":"official","path":"src/Google12/network.py","file_url":"https://github.com/tk-rusch/lem/blob/HEAD/src/Google12/network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9cfb904b319e5586"}},{"code_sha256_prefix":"2c67d2b0758d5fe0","entry":"evaluate_deterministic","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/evaluation.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/evaluation.py","link_basis":"harvester_set","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":"2c67d2b0758d5fe0"}},{"code_sha256_prefix":"c598ebd47e698d5c","entry":"evaluate_mc_with_geometric_mean","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/evaluation.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/evaluation.py","link_basis":"harvester_set","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":"c598ebd47e698d5c"}},{"code_sha256_prefix":"184a036257da4448","entry":"evaluate_mc_with_power_mean","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/evaluation.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/evaluation.py","link_basis":"harvester_set","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":"184a036257da4448"}},{"code_sha256_prefix":"db14e2261c3a6e84","entry":"handle_config_defaults","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/lamb_flags.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/lamb_flags.py","link_basis":"harvester_set","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":"db14e2261c3a6e84"}},{"code_sha256_prefix":"41b09314d9718a2f","entry":"maybe_truncate","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/corpus.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/corpus.py","link_basis":"harvester_set","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":"41b09314d9718a2f"}},{"code_sha256_prefix":"e9fa8fcbfffec562","entry":"option_visibility","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/lamb_flags.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/lamb_flags.py","link_basis":"harvester_set","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":"e9fa8fcbfffec562"}},{"code_sha256_prefix":"e82bc4ce41514342","entry":"read_character_based_corpus","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/corpus.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/corpus.py","link_basis":"harvester_set","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":"e82bc4ce41514342"}},{"code_sha256_prefix":"d52c0a249edc34f9","entry":"read_word_based_corpus","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/corpus.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/corpus.py","link_basis":"harvester_set","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":"d52c0a249edc34f9"}},{"code_sha256_prefix":"fe22ebdbafcd2a30","entry":"round_to_int","repo":"deepmind/lamb","repo_kind":"found_in_text","path":"lamb/lamb_flags.py","file_url":"https://github.com/deepmind/lamb/blob/HEAD/lamb/lamb_flags.py","link_basis":"harvester_set","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":"fe22ebdbafcd2a30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}