{"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/multi-timescale-memory-dynamics-in-a","title":"Multi-timescale memory dynamics in a reinforcement learning network with attention-gated memory","arxiv_id":"1712.10062","date":"2017-12-28","proceeding":null,"authors":["Marco Martinolli","Wulfram Gerstner","Aditya Gilra"],"abstract":"Learning and memory are intertwined in our brain and their relationship is at\nthe core of several recent neural network models. In particular, the\nAttention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning\nnetwork with an emphasis on biological plausibility of memory dynamics and\nlearning. We find that the AuGMEnT network does not solve some hierarchical\ntasks, where higher-level stimuli have to be maintained over a long time, while\nlower-level stimuli need to be remembered and forgotten over a shorter\ntimescale. To overcome this limitation, we introduce hybrid AuGMEnT, with leaky\nor short-timescale and non-leaky or long-timescale units in memory, that allow\nto exchange lower-level information while maintaining higher-level one, thus\nsolving both hierarchical and distractor tasks.","url_abs":"http://arxiv.org/abs/1712.10062v1","url_pdf":"http://arxiv.org/pdf/1712.10062v1.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":"multi-timescale-memory-dynamics-in-a","repo_url":"https://github.com/martin592/hybrid_AuGMEnT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multi-timescale-memory-dynamics-in-a","repo_url":"https://github.com/adityagilra/archibrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}