{"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/lstm-a-search-space-odyssey","title":"LSTM: A Search Space Odyssey","arxiv_id":"1503.04069","date":"2015-03-13","proceeding":null,"authors":["Klaus Greff","Rupesh Kumar Srivastava","Jan Koutník","Bas R. Steunebrink","Jürgen Schmidhuber"],"abstract":"Several variants of the Long Short-Term Memory (LSTM) architecture for\nrecurrent neural networks have been proposed since its inception in 1995. In\nrecent years, these networks have become the state-of-the-art models for a\nvariety of machine learning problems. This has led to a renewed interest in\nunderstanding the role and utility of various computational components of\ntypical LSTM variants. In this paper, we present the first large-scale analysis\nof eight LSTM variants on three representative tasks: speech recognition,\nhandwriting recognition, and polyphonic music modeling. The hyperparameters of\nall LSTM variants for each task were optimized separately using random search,\nand their importance was assessed using the powerful fANOVA framework. In\ntotal, we summarize the results of 5400 experimental runs ($\\approx 15$ years\nof CPU time), which makes our study the largest of its kind on LSTM networks.\nOur results show that none of the variants can improve upon the standard LSTM\narchitecture significantly, and demonstrate the forget gate and the output\nactivation function to be its most critical components. We further observe that\nthe studied hyperparameters are virtually independent and derive guidelines for\ntheir efficient adjustment.","url_abs":"http://arxiv.org/abs/1503.04069v2","url_pdf":"http://arxiv.org/pdf/1503.04069v2.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":"lstm-a-search-space-odyssey","repo_url":"https://github.com/RohanAsnani/capstone_project_machine_learning-nanodegree","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/a-martyn/unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/alexandrujeman/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/alexjeman/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/disooqi/DNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/disooqi/Natasy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/flukeskywalker/highway-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/hadi-gharibi/pytorch-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/kevin28520/RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/sw-scot/foco-mlmis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/tmatha/lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/widmi/widis-lstm-tools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/2023-MindSpore-1/ms-code-14/tree/main/LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/2023-MindSpore-1/ms-code-219/tree/main/atae_lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/cui0523/Code6/tree/main/atae_lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/yangyucheng000/Paper-2/tree/main/lstm-gaf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"lstm-a-search-space-odyssey","repo_url":"https://github.com/yangyucheng000/papercode-2/tree/main/lstm-gaf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"handwriting-recognition","task_name":"Handwriting Recognition"},{"task_slug":"music-modeling","task_name":"Music Modeling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1503.04069","atlas_url":"https://app.syntology.ai/?focus=1503.04069","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":"1503.04069"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1503.04069\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1503.04069"},"call":"get_concepts_for_paper(arxiv_id=\"1503.04069\")"}],"by_repo":[{"repo":"RohanAsnani/capstone_project_machine_learning-nanodegree","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"a-martyn/unet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1505.04597"],"harvested_for_calls":[{"arxiv_id":"1505.04597","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.04597"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.04597\")"}]},{"repo":"alexandrujeman/dqn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alexjeman/dqn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"disooqi/DNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"disooqi/Natasy","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"flukeskywalker/highway-networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hadi-gharibi/pytorch-lstm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kevin28520/RNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sw-scot/foco-mlmis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tmatha/lstm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"widmi/widis-lstm-tools","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-14","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-219","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cui0523/Code6","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yangyucheng000/Paper-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yangyucheng000/papercode-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2202.10108"],"harvested_for_calls":[{"arxiv_id":"2202.10108","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.10108"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.10108\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"594f995546132787584e0b841021f7af730c0fb1ff3d12ae4d6ddd2d3b8fc829","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}