2026-09-25T03:03:37Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/83242022-01-13T07:55:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Bruce M. Blumberg and Alex P. Pentland. Ivanov, Yuri A., 1967- Massachusetts Institute of Technology. Dept. of Architecture. Program in Media Arts and Sciences. Program in Media Arts and Sciences (Massachusetts Institute of Technology) 2005-08-23T19:12:03Z 2005-08-23T19:12:03Z 2002 2002 http://hdl.handle.net/1721.1/8324 50490379 Thesis (Ph. D.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2002. Includes bibliographical references (p. 163-171). This thesis is devoted to the study of algorithms for early perceptual learning for an autonomous agent in the presence of feedback. In the framework of associative perceptual learning with indirect supervision, three learning techniques are examined in detail: * short-term on-line memory-based model learning; * long-term on-line distribution-based statistical estimation; * mixed on- and off-line continuous learning of gesture models. The three methods proceed within essentially the same framework, consisting of a perceptual sub-system and a sub-system that implements the associative mapping from perceptual categories to actions. The thesis contributes in several areas - it formulates the framework for solving incremental associative learning tasks; introduces the idea of incremental classification with utility, margin and boundary compression rules; develops a technique of sequence classification with Support Vector Machines; introduces an idea of weak transduction and offers an EM-based algorithm for solving it; proposes a mixed on- and off-line algorithm for learning continuous gesture with reward-based decomposition of the state space. The proposed framework facilitates the development of agents and human-computer interfaces that can be trained by a naive user. The work presented in this dissertation focuses on making these incremental learning algorithms practical. by Yuri A. Ivanov. Ph.D. 171 p. 11010451 bytes 11010208 bytes application/pdf application/pdf eng Massachusetts Institute of Technology M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 Architecture. Program in Media Arts and Sciences. State discovery for autonomous learning Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8cffe7c0-cef1-4229-a56c-4919695928b2"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>State discovery for autonomous learning</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2002</PublicationDate> <Authors> <Author> <DisplayName>Ivanov, Yuri A., 1967-</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Architecture. Program in Media Arts and Sciences.</Keyword> <Abstract>This thesis is devoted to the study of algorithms for early perceptual learning for an autonomous agent in the presence of feedback. In the framework of associative perceptual learning with indirect supervision, three learning techniques are examined in detail: * short-term on-line memory-based model learning; * long-term on-line distribution-based statistical estimation; * mixed on- and off-line continuous learning of gesture models. The three methods proceed within essentially the same framework, consisting of a perceptual sub-system and a sub-system that implements the associative mapping from perceptual categories to actions. The thesis contributes in several areas - it formulates the framework for solving incremental associative learning tasks; introduces the idea of incremental classification with utility, margin and boundary compression rules; develops a technique of sequence classification with Support Vector Machines; introduces an idea of weak transduction and offers an EM-based algorithm for solving it; proposes a mixed on- and off-line algorithm for learning continuous gesture with reward-based decomposition of the state space. The proposed framework facilitates the development of agents and human-computer interfaces that can be trained by a naive user. The work presented in this dissertation focuses on making these incremental learning algorithms practical.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>