{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/subregular-complexity-and-deep-learning","title":"Subregular Complexity and Deep Learning","arxiv_id":"1705.05940","date":"2017-05-16","proceeding":null,"authors":["Enes Avcu","Chihiro Shibata","Jeffrey Heinz"],"abstract":"This paper argues that the judicial use of formal language theory and\ngrammatical inference are invaluable tools in understanding how deep neural\nnetworks can and cannot represent and learn long-term dependencies in temporal\nsequences. Learning experiments were conducted with two types of Recurrent\nNeural Networks (RNNs) on six formal languages drawn from the Strictly Local\n(SL) and Strictly Piecewise (SP) classes. The networks were Simple RNNs\n(s-RNNs) and Long Short-Term Memory RNNs (LSTMs) of varying sizes. The SL and\nSP classes are among the simplest in a mathematically well-understood hierarchy\nof subregular classes. They encode local and long-term dependencies,\nrespectively. The grammatical inference algorithm Regular Positive and Negative\nInference (RPNI) provided a baseline. According to earlier research, the LSTM\narchitecture should be capable of learning long-term dependencies and should\noutperform s-RNNs. The results of these experiments challenge this narrative.\nFirst, the LSTMs' performance was generally worse in the SP experiments than in\nthe SL ones. Second, the s-RNNs out-performed the LSTMs on the most complex SP\nexperiment and performed comparably to them on the others.","url_abs":"http://arxiv.org/abs/1705.05940v3","url_pdf":"http://arxiv.org/pdf/1705.05940v3.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":"subregular-complexity-and-deep-learning","repo_url":"https://github.com/enesavc/subreg_deeplearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.05940","atlas_url":"https://app.syntology.ai/?focus=1705.05940","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1705.05940"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1705.05940\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1705.05940"},"call":"get_concepts_for_paper(arxiv_id=\"1705.05940\")"}],"by_repo":[{"repo":"enesavc/subreg_deeplearning","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"abf0b9f12531432f525948ce9ec73c52a7b575f6332ac9f5abc1654ca77b1e60","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}