Show simple item record

dc.contributor.authorSalge, Christoph
dc.contributor.authorPolani, D.
dc.date.accessioned2011-08-15T11:01:57Z
dc.date.available2011-08-15T11:01:57Z
dc.date.issued2008
dc.identifier.citationSalge , C & Polani , D 2008 , Information-driven organization of visual receptive fields . in In: Proceedings of the GWAL-8, 8th German Workshop on Artificial Life 2008 . Akademische Verlagsgesellschaft .
dc.identifier.isbn978-3-89838-613-5
dc.identifier.otherPURE: 304871
dc.identifier.otherPURE UUID: 0af0f204-8add-4a89-ad14-b5b2656e28a0
dc.identifier.urihttp://hdl.handle.net/2299/6207
dc.descriptionCopyright Akademische Verlagsgesellschaft
dc.description.abstractBy using information theory to reduce the state space of sensor arrays, such as receptive fields, for AI decision making we offer an adaptive algorithm without classical biases of hand coded approaches. This paper presents a way to build an acyclic directed graph to organise the sensor inputs of a visual receptive field. The Information Distance Metric is used to repeatedly select two sensors, which contain the most information about each other. Those are then encoded to a single variable, of equal alphabet size, with a deterministic mapping function that aims to create maximal entropy while maintaining a low information distance to the original sensors. The resulting tree determines which sensors are fused to reduce the input data while maintaining a maximum of information. The structure adapts to different environments of input images by encoding groups of preferred line structures or creating a higher resolution for areas with simulated movement. These effects are created without prior assumptions about the sensor statistics or the spatial configuration of the receptive field, and are cheap to compute since only pairwise informational comparison of sensors is used.en
dc.language.isoeng
dc.publisherAkademische Verlagsgesellschaft
dc.relation.ispartofIn: Proceedings of the GWAL-8, 8th German Workshop on Artificial Life 2008
dc.rightsOpen
dc.subjectinformation theory
dc.subjectadaptive sensors
dc.titleInformation-driven organization of visual receptive fieldsen
dc.contributor.institutionScience & Technology Research Institute
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionCentre for Computer Science and Informatics Research
dc.contributor.institutionAdaptive Systems
dc.relation.schoolSchool of Computer Science
dc.description.versiontypeFinal Accepted Version
dcterms.dateAccepted2008
rioxxterms.versionAM
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeOpen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record