Show simple item record

dc.contributor.authorÖzkural, Erayen_US
dc.coverage.spatialMountain View, CA, USAen_US
dc.date.accessioned2016-02-08T12:19:00Z
dc.date.available2016-02-08T12:19:00Z
dc.date.issued2011en_US
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/11693/28377
dc.descriptionDate of Conference: August 3-6, 2011en_US
dc.descriptionConference name: 4th International Conference, AGI 2011en_US
dc.description.abstractWe propose a long-term memory design for artificial general intelligence based on Solomonoff's incremental machine learning methods. We introduce four synergistic update algorithms that use a Stochastic Context-Free Grammar as a guiding probability distribution of programs. The update algorithms accomplish adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. A controlled experiment with a long training sequence shows that our incremental learning approach is effective. © 2011 Springer-Verlag Berlin Heidelberg.en_US
dc.language.isoEnglishen_US
dc.source.titleArtificial General Intelligenceen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/978-3-642-22887-2_47en_US
dc.relation.isversionofhttps://doi.org/10.1007/978-3-642-22887-2en_US
dc.subjectControlled experimenten_US
dc.subjectGeneral Intelligenceen_US
dc.subjectIncremental learningen_US
dc.subjectLearning programmingen_US
dc.subjectLong term memoryen_US
dc.subjectMachine learning methodsen_US
dc.subjectStochastic context free grammaren_US
dc.subjectSubprogramsen_US
dc.subjectTraining sequencesen_US
dc.subjectAlgorithmsen_US
dc.subjectContext free grammarsen_US
dc.subjectLearning systemsen_US
dc.subjectProbability distributionsen_US
dc.subjectHeuristic methodsen_US
dc.titleTowards heuristic algorithmic memoryen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineering
dc.citation.spage382en_US
dc.citation.epage387en_US
dc.citation.volumeNumber6830en_US
dc.identifier.doi10.1007/978-3-642-22887-2_47en_US
dc.identifier.doi10.1007/978-3-642-22887-2en_US
dc.publisherSpringer, Berlin, Heidelbergen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record