Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorBroersen, Jan
dc.contributor.advisorVreeswijk, Gerard
dc.contributor.advisorGrabmayer, Clemens
dc.contributor.authorMatser, J.E.
dc.date.accessioned2011-05-02T17:00:42Z
dc.date.available2011-05-02
dc.date.available2011-05-02T17:00:42Z
dc.date.issued2011
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/6938
dc.description.abstractIn this thesis we look at improving the performance of Liquid State Machines on a speech recognition and a music recognition task, by making structural changes to the liquid. The changes are designed, rather than evolved or learnt, to have more insight into what the effect of particular changes on performance are. We conclude that the effect of any designed structural changes is far outweighed by the random generation of liquids and that the evaluation of LSMs should focus on using sufficiently complex and preferably realistic tasks.
dc.description.sponsorshipUtrecht University
dc.format.extent1401148 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleStructured Liquids in Liquid State Machines
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsLSM, Liquid State Machine, Music Recognition, Speech Recognition, Maass, Natschläger, Markram, Bach, Beethoven, Spiking Neural Networks, Supervised Learning, Time Series
dc.subject.courseuuCognitive Artificial Intelligence


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record