{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T14:27:15Z","timestamp":1761488835899,"version":"3.38.0"},"reference-count":17,"publisher":"Wiley","license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Robotics"],"published-print":{"date-parts":[[2011]]},"abstract":"<jats:p>Theoretical entities are aspects of the world that cannot be sensed directly but that, nevertheless, are causally relevant. Scientific inquiry has uncovered many such entities, such as black holes and dark matter. We claim that theoretical entities, or hidden variables, are important for the development of concepts within the lifetime of an individual and present a novel neural network architecture that solves three problems related to theoretical entities: (1) discovering that they exist, (2) determining their number, and (3) computing their values. Experiments show the utility of the proposed approach using discrete time dynamical systems, in which some of the state variables are hidden, and sensor data obtained from the camera of a mobile robot, in which the sizes and locations of objects in the visual field are observed but their sizes and locations (distances) in the three-dimensional world are not. Two different regularization terms are explored that improve the network's ability to approximate the values of hidden variables, and the performance and capabilities of the network are compared to that of Hidden Markov Models.<\/jats:p>","DOI":"10.1155\/2011\/193146","type":"journal-article","created":{"date-parts":[[2012,1,3]],"date-time":"2012-01-03T23:18:44Z","timestamp":1325632724000},"page":"1-16","source":"Crossref","is-referenced-by-count":1,"title":["Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net"],"prefix":"10.1155","volume":"2011","author":[{"given":"Soumi","family":"Ray","sequence":"first","affiliation":[{"name":"Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, 1000 Hilltop Circle, Baltimore, MD 21250, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Oates","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, 1000 Hilltop Circle, Baltimore, MD 21250, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"year":"1993","key":"1"},{"issue":"2","key":"2","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1023\/A:1022622132310","volume":"14","year":"1994","journal-title":"Machine Learning"},{"year":"2001","key":"3"},{"key":"4","first-page":"524","volume":"2","year":"1990","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","year":"1977","journal-title":"Journal of the Royal Statistical Society Series B"},{"issue":"1-2","key":"7","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","year":"1998","journal-title":"Artificial Intelligence"},{"volume":"14","volume-title":"Predictive representations of state","year":"2002","key":"8"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/176584.176589"},{"volume":"7","volume-title":"Instance-based state identification for reinforcement learning","year":"1994","key":"11"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"volume-title":"Gaussian process dynamical models","year":"2006","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.53.100901.135239"},{"year":"1998","key":"15"},{"journal-title":"Lecture Notes in Mathematics","first-page":"366","year":"1981","key":"16"},{"journal-title":"Journal of Atmospheric Science","year":"1963","key":"18"},{"volume-title":"Slow, decorrelated features for pretraining complex cell-like networks","year":"2009","key":"21"},{"issue":"1","key":"22","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","volume":"3","year":"1986","journal-title":"IEEE ASSP Magazine"}],"container-title":["Journal of Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2011\/193146.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2011\/193146.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2011\/193146.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T14:38:46Z","timestamp":1742222326000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.hindawi.com\/journals\/jr\/2011\/193146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"references-count":17,"alternative-id":["193146","193146"],"URL":"https:\/\/doi.org\/10.1155\/2011\/193146","relation":{},"ISSN":["1687-9600","1687-9619"],"issn-type":[{"type":"print","value":"1687-9600"},{"type":"electronic","value":"1687-9619"}],"subject":[],"published":{"date-parts":[[2011]]}}}