{"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/a-simple-way-to-initialize-recurrent-networks","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","arxiv_id":"1504.00941","date":"2015-04-03","proceeding":null,"authors":["Quoc V. Le","Navdeep Jaitly","Geoffrey E. Hinton"],"abstract":"Learning long term dependencies in recurrent networks is difficult due to\nvanishing and exploding gradients. To overcome this difficulty, researchers\nhave developed sophisticated optimization techniques and network architectures.\nIn this paper, we propose a simpler solution that use recurrent neural networks\ncomposed of rectified linear units. Key to our solution is the use of the\nidentity matrix or its scaled version to initialize the recurrent weight\nmatrix. We find that our solution is comparable to LSTM on our four benchmarks:\ntwo toy problems involving long-range temporal structures, a large language\nmodeling problem and a benchmark speech recognition problem.","url_abs":"http://arxiv.org/abs/1504.00941v2","url_pdf":"http://arxiv.org/pdf/1504.00941v2.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":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/adamx97/Data-Science-Advanced-Capstone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/facebookresearch/salina","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/minhtriet/gridworld","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/sobhan-moosavi/characterizingdrivingstyleswithdeeplearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-simple-way-to-initialize-recurrent-networks","repo_url":"https://github.com/trevor-richardson/rnn_zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"speech-recognition-1","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":[{"leaderboard":"/sota/sequential-image-classification-on-sequential","task":"Sequential Image Classification","dataset":"Sequential MNIST","model":"iRNN","rank_in_archive_order":27,"of":30,"metrics":{"Permuted Accuracy":"82%","Unpermuted Accuracy":"97%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1504.00941","atlas_url":"https://app.syntology.ai/?focus=1504.00941","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":"1504.00941"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1504.00941\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1504.00941"},"call":"get_concepts_for_paper(arxiv_id=\"1504.00941\")"}],"by_repo":[{"repo":"adamx97/Data-Science-Advanced-Capstone","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/salina","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2106.01345","2110.14457"],"harvested_for_calls":[{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2110.14457","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.14457"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.14457\")"}]},{"repo":"mindspore-courses/DeepNLP-models-MindSpore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"minhtriet/gridworld","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sobhan-moosavi/characterizingdrivingstyleswithdeeplearning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"trevor-richardson/rnn_zoo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1406.1078"],"harvested_for_calls":[{"arxiv_id":"1406.1078","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1406.1078"},"call":"get_harvested_code_for_paper(arxiv_id=\"1406.1078\")"}]}],"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":"09ca93624e9f4fe9cea0f39617439f26ee9940096ecd79ea6302c0247af2fb22","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}