{"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/recurrent-memory-array-structures","title":"Recurrent Memory Array Structures","arxiv_id":"1607.03085","date":"2016-07-11","proceeding":null,"authors":["Kamil Rocki"],"abstract":"The following report introduces ideas augmenting standard Long Short Term\nMemory (LSTM) architecture with multiple memory cells per hidden unit in order\nto improve its generalization capabilities. It considers both deterministic and\nstochastic variants of memory operation. It is shown that the nondeterministic\nArray-LSTM approach improves state-of-the-art performance on character level\ntext prediction achieving 1.402 BPC on enwik8 dataset. Furthermore, this report\nestabilishes baseline neural-based results of 1.12 BPC and 1.19 BPC for enwik9\nand enwik10 datasets respectively.","url_abs":"http://arxiv.org/abs/1607.03085v3","url_pdf":"http://arxiv.org/pdf/1607.03085v3.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":"recurrent-memory-array-structures","repo_url":"https://github.com/krocki/ArrayLSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"recurrent-memory-array-structures","repo_url":"https://github.com/Thijsvanede/ArrayLSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}