Show simple item record

dc.contributor.advisorBruce M. Blumberg.en_US
dc.contributor.authorLyons, Derek Eugenen_US
dc.contributor.otherMassachusetts Institute of Technology. Dept. of Architecture. Program in Media Arts and Sciences.en_US
dc.date.accessioned2005-06-02T18:49:06Z
dc.date.available2005-06-02T18:49:06Z
dc.date.copyright2004en_US
dc.date.issued2004en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/17824
dc.descriptionThesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2004.en_US
dc.descriptionPage 205 blank.en_US
dc.descriptionIncludes bibliographical references (p. [197]-204).en_US
dc.description.abstractCognitive development is one of nature's most important mechanisms for creating robustly adaptive intelligent creatures. From felids to oscines, developing animals are capable of learning in adverse environments with a reliability that often outpaces the current state-of-the-art in artificial intelligence (AI) The purpose of this thesis, therefore, is to examine how insights from cognitive development might be applied to the design of AI architectures. Starting with a targeted review of the ethological literature, I identify the key computational lessons of development, the fundamental conceptual insights that suggest intriguing new strategies for behavioral organization. These insights are then employed in the design of a developmental behavior architecture in which a hierarchical motivation-based behavior system is coupled to a distributed set of domain-specific learning tools. The architecture is deployed in a synthetic character (Hektor the mouse) whose challenge is to learn to play a competitive card matching game successfully against a human user. Evaluation of Hektor's performance on this task, at both qualitative and quantitative levels of description, reveal that the developmental architecture is capable of surmounting complex learning objectives in a novel and efficient manner. I conclude that the architecture presented here represents a valuable starting point for further consideration of developmental design principles.en_US
dc.description.statementofresponsibilityby Derek Eugen Lyons.en_US
dc.format.extent205 p.en_US
dc.format.extent7564590 bytes
dc.format.extent7589626 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypeapplication/pdf
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.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.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582
dc.subjectArchitecture. Program in Media Arts and Sciences.en_US
dc.titleGrowing up virtual : the computational lessons of developmenten_US
dc.typeThesisen_US
dc.description.degreeS.M.en_US
dc.contributor.departmentProgram in Media Arts and Sciences (Massachusetts Institute of Technology)
dc.identifier.oclc56564997en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record