{"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/simplified-gating-in-long-short-term-memory","title":"Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks","arxiv_id":"1701.03441","date":"2017-01-12","proceeding":null,"authors":["Yuzhen Lu","Fathi M. Salem"],"abstract":"The standard LSTM recurrent neural networks while very powerful in long-range\ndependency sequence applications have highly complex structure and relatively\nlarge (adaptive) parameters. In this work, we present empirical comparison\nbetween the standard LSTM recurrent neural network architecture and three new\nparameter-reduced variants obtained by eliminating combinations of the input\nsignal, bias, and hidden unit signals from individual gating signals. The\nexperiments on two sequence datasets show that the three new variants, called\nsimply as LSTM1, LSTM2, and LSTM3, can achieve comparable performance to the\nstandard LSTM model with less (adaptive) parameters.","url_abs":"http://arxiv.org/abs/1701.03441v1","url_pdf":"http://arxiv.org/pdf/1701.03441v1.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":"simplified-gating-in-long-short-term-memory","repo_url":"https://github.com/jingweimo/Modified-LSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"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":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}