{"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/fast-slow-recurrent-neural-networks","title":"Fast-Slow Recurrent Neural Networks","arxiv_id":"1705.08639","date":"2017-05-24","proceeding":"NeurIPS 2017 12","authors":["Asier Mujika","Florian Meier","Angelika Steger"],"abstract":"Processing sequential data of variable length is a major challenge in a wide\nrange of applications, such as speech recognition, language modeling,\ngenerative image modeling and machine translation. Here, we address this\nchallenge by proposing a novel recurrent neural network (RNN) architecture, the\nFast-Slow RNN (FS-RNN). The FS-RNN incorporates the strengths of both\nmultiscale RNNs and deep transition RNNs as it processes sequential data on\ndifferent timescales and learns complex transition functions from one time step\nto the next. We evaluate the FS-RNN on two character level language modeling\ndata sets, Penn Treebank and Hutter Prize Wikipedia, where we improve state of\nthe art results to $1.19$ and $1.25$ bits-per-character (BPC), respectively. In\naddition, an ensemble of two FS-RNNs achieves $1.20$ BPC on Hutter Prize\nWikipedia outperforming the best known compression algorithm with respect to\nthe BPC measure. We also present an empirical investigation of the learning and\nnetwork dynamics of the FS-RNN, which explains the improved performance\ncompared to other RNN architectures. Our approach is general as any kind of RNN\ncell is a possible building block for the FS-RNN architecture, and thus can be\nflexibly applied to different tasks.","url_abs":"http://arxiv.org/abs/1705.08639v2","url_pdf":"http://arxiv.org/pdf/1705.08639v2.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":"fast-slow-recurrent-neural-networks","repo_url":"https://github.com/amujika/Fast-Slow-LSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-hutter-prize","task":"Language Modelling","dataset":"Hutter Prize","model":"Large FS-LSTM-4","rank_in_archive_order":15,"of":18,"metrics":{"Bit per Character (BPC)":"1.245","Number of params":"47M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-hutter-prize","task":"Language Modelling","dataset":"Hutter Prize","model":"FS-LSTM-4","rank_in_archive_order":17,"of":18,"metrics":{"Bit per Character (BPC)":"1.277","Number of params":"27M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"FS-LSTM-4","rank_in_archive_order":10,"of":20,"metrics":{"Bit per Character (BPC)":"1.190","Number of params":"27M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"FS-LSTM-2","rank_in_archive_order":12,"of":20,"metrics":{"Bit per Character (BPC)":"1.193","Number of params":"27M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-enwiki8","task":"Language Modelling","dataset":"enwik8","model":"Large FS-LSTM-4","rank_in_archive_order":35,"of":42,"metrics":{"Bit per Character (BPC)":" 1.25","Number of params":"47M"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.08639","atlas_url":"https://app.syntology.ai/?focus=1705.08639","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":"1705.08639"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1705.08639\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1705.08639"},"call":"get_concepts_for_paper(arxiv_id=\"1705.08639\")"}],"by_repo":[{"repo":"amujika/Fast-Slow-LSTM","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":"7df72317165f437a25d56d0dec4d512d64e6deb53df4f07b4a09e56c793d6692","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}