{"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/the-statistical-recurrent-unit","title":"The Statistical Recurrent Unit","arxiv_id":"1703.00381","date":"2017-03-01","proceeding":"ICML 2017 8","authors":["Junier B. Oliva","Barnabas Poczos","Jeff Schneider"],"abstract":"Sophisticated gated recurrent neural network architectures like LSTMs and\nGRUs have been shown to be highly effective in a myriad of applications. We\ndevelop an un-gated unit, the statistical recurrent unit (SRU), that is able to\nlearn long term dependencies in data by only keeping moving averages of\nstatistics. The SRU's architecture is simple, un-gated, and contains a\ncomparable number of parameters to LSTMs; yet, SRUs perform favorably to more\nsophisticated LSTM and GRU alternatives, often outperforming one or both in\nvarious tasks. We show the efficacy of SRUs as compared to LSTMs and GRUs in an\nunbiased manner by optimizing respective architectures' hyperparameters in a\nBayesian optimization scheme for both synthetic and real-world tasks.","url_abs":"http://arxiv.org/abs/1703.00381v1","url_pdf":"http://arxiv.org/pdf/1703.00381v1.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":"the-statistical-recurrent-unit","repo_url":"https://github.com/mirandawork/sru","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"the-statistical-recurrent-unit","repo_url":"https://github.com/Selozhd/UngatedRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=1703.00381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}