dc.rights.license | CC-BY-NC-ND | |
dc.contributor.advisor | Broersen, Jan | |
dc.contributor.advisor | Vreeswijk, Gerard | |
dc.contributor.advisor | Grabmayer, Clemens | |
dc.contributor.author | Matser, J.E. | |
dc.date.accessioned | 2011-05-02T17:00:42Z | |
dc.date.available | 2011-05-02 | |
dc.date.available | 2011-05-02T17:00:42Z | |
dc.date.issued | 2011 | |
dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/6938 | |
dc.description.abstract | In 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.sponsorship | Utrecht University | |
dc.format.extent | 1401148 bytes | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.title | Structured Liquids in Liquid State Machines | |
dc.type.content | Master Thesis | |
dc.rights.accessrights | Open Access | |
dc.subject.keywords | LSM, Liquid State Machine, Music Recognition, Speech Recognition, Maass, Natschläger, Markram, Bach, Beethoven, Spiking Neural Networks, Supervised Learning, Time Series | |
dc.subject.courseuu | Cognitive Artificial Intelligence | |