Logo des Repositoriums
 

Geometric Design Principles for Brains of Embodied Agents

Kurzanzeige
dc.contributor.authorAy, Nihat
dc.date.accessioned2018-01-08T09:18:05Z
dc.date.available2018-01-08T09:18:05Z
dc.date.issued2015
dc.description.abstractI propose a formal model of the sensorimotor loop and discuss corresponding extrinsic embodiment constraints and the intrinsic degrees of freedom. These degrees constitute the basis for adaptation in terms of learning and should therefore be coupled with the embodiment constraints. Notions of sufficiency and embodied universal approximation allow us to formulate principles for such a coupling. This provides a geometric approach to the design of control architectures for embodied agents.
dc.identifier.pissn1610-1987
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/11482
dc.publisherSpringer
dc.relation.ispartofKI - Künstliche Intelligenz: Vol. 29, No. 4
dc.relation.ispartofseriesKI - Künstliche Intelligenz
dc.subjectCheap design
dc.subjectEmbodiment
dc.subjectInformation geometry
dc.subjectSensorimotor loop
dc.subjectUniversal approximation
dc.titleGeometric Design Principles for Brains of Embodied Agents
dc.typeText/Journal Article
gi.citation.endPage399
gi.citation.startPage389

Dateien

Sammlungen

Künstliche Intelligenz 29(4) - November 2015