{"file_date_updated":"2022-01-26T11:08:51Z","_id":"10673","department":[{"_id":"GradSch"},{"_id":"ToHe"}],"quality_controlled":"1","oa_version":"Published Version","author":[{"first_name":"Ramin","full_name":"Hasani, Ramin","last_name":"Hasani"},{"last_name":"Lechner","full_name":"Lechner, Mathias","first_name":"Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Amini","full_name":"Amini, Alexander","first_name":"Alexander"},{"full_name":"Rus, Daniela","last_name":"Rus","first_name":"Daniela"},{"first_name":"Radu","full_name":"Grosu, Radu","last_name":"Grosu"}],"status":"public","has_accepted_license":"1","date_published":"2020-01-01T00:00:00Z","scopus_import":"1","alternative_title":["PMLR"],"series_title":"PMLR","oa":1,"title":"A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits","license":"https://creativecommons.org/licenses/by-nc-nd/3.0/","publication_status":"published","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","page":"4082-4093","conference":{"start_date":"2020-07-12","end_date":"2020-07-18","name":"ML: Machine Learning","location":"Virtual"},"publication_identifier":{"issn":["2640-3498"]},"tmp":{"name":"Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)","short":"CC BY-NC-ND (3.0)","image":"/images/cc_by_nc_nd.png","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode"},"type":"conference","main_file_link":[{"url":"http://proceedings.mlr.press/v119/hasani20a.html","open_access":"1"}],"file":[{"content_type":"application/pdf","success":1,"creator":"cchlebak","file_id":"10691","date_created":"2022-01-26T11:08:51Z","checksum":"c9a4a29161777fc1a89ef451c040e3b1","file_name":"2020_PMLR_Hasani.pdf","file_size":2329798,"date_updated":"2022-01-26T11:08:51Z","access_level":"open_access","relation":"main_file"}],"citation":{"ieee":"R. Hasani, M. Lechner, A. Amini, D. Rus, and R. Grosu, “A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits,” in <i>Proceedings of the 37th International Conference on Machine Learning</i>, Virtual, 2020, pp. 4082–4093.","apa":"Hasani, R., Lechner, M., Amini, A., Rus, D., &#38; Grosu, R. (2020). A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. In <i>Proceedings of the 37th International Conference on Machine Learning</i> (pp. 4082–4093). Virtual.","chicago":"Hasani, Ramin, Mathias Lechner, Alexander Amini, Daniela Rus, and Radu Grosu. “A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits.” In <i>Proceedings of the 37th International Conference on Machine Learning</i>, 4082–93. PMLR, 2020.","short":"R. Hasani, M. Lechner, A. Amini, D. Rus, R. Grosu, in:, Proceedings of the 37th International Conference on Machine Learning, 2020, pp. 4082–4093.","ama":"Hasani R, Lechner M, Amini A, Rus D, Grosu R. A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. In: <i>Proceedings of the 37th International Conference on Machine Learning</i>. PMLR. ; 2020:4082-4093.","ista":"Hasani R, Lechner M, Amini A, Rus D, Grosu R. 2020. A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. Proceedings of the 37th International Conference on Machine Learning. ML: Machine LearningPMLR, PMLR, , 4082–4093.","mla":"Hasani, Ramin, et al. “A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits.” <i>Proceedings of the 37th International Conference on Machine Learning</i>, 2020, pp. 4082–93."},"abstract":[{"lang":"eng","text":"We propose a neural information processing system obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce ordinary neural circuits (ONCs), defined as the model of biological neural circuits reparameterized for the control of alternative tasks. We first demonstrate that ONCs realize networks with higher maximum flow compared to arbitrary wired networks. We then learn instances of ONCs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Ordinary neural circuits perform on par and, in some cases, significantly surpass the performance of contemporary deep learning models. ONC networks are compact, 77% sparser than their counterpart neural controllers, and their neural dynamics are fully interpretable at the cell-level."}],"date_created":"2022-01-25T15:50:34Z","publication":"Proceedings of the 37th International Conference on Machine Learning","year":"2020","project":[{"name":"The Wittgenstein Prize","_id":"25F42A32-B435-11E9-9278-68D0E5697425","grant_number":"Z211","call_identifier":"FWF"}],"date_updated":"2022-01-26T11:14:27Z","language":[{"iso":"eng"}],"acknowledgement":"RH and RG are partially supported by Horizon-2020 ECSEL Project grant No. 783163 (iDev40), Productive 4.0, and ATBMBFW CPS-IoT Ecosystem. ML was supported in part by the Austrian Science Fund (FWF) under grant Z211-N23\r\n(Wittgenstein Award). AA is supported by the National Science Foundation (NSF) Graduate Research Fellowship\r\nProgram. RH and DR are partially supported by The Boeing Company and JP Morgan Chase. This research work is\r\npartially drawn from the PhD dissertation of RH.\r\n","ddc":["000"],"article_processing_charge":"No"}