Reservoir computing based on delay-dynamical systems

Appeltant, Lennert

Home
→
Producció científica
→
Tesis doctorals
→
View Item

dc.contributor	Danckaert, Jan
dc.contributor	Departament de Física
dc.creator	Appeltant, Lennert
dc.date	2012
dc.date.accessioned	2017-07-10T09:36:19Z
dc.date.available	2017-07-10T09:36:19Z
dc.identifier	http://ibdigital.uib.cat/greenstone/collect/tesisUIB/index/assoc/TDX-1080/3-84144.dir/TDX-10803-84144.pdf
dc.identifier.uri	http://hdl.handle.net/11201/2487
dc.description	[eng] Today, except for mathematical operations, our brain functions much faster and more efficient than any supercomputer. It is precisely this form of information processing in neural networks that inspires researchers to create systems that mimic the brain’s information processing capabilities. In this thesis we propose a novel approach to implement these alternative computer architectures, based on delayed feedback. We show that one single nonlinear node with delayed feedback can replace a large network of nonlinear nodes. First we numerically investigate the architecture and performance of delayed feedback systems as information processing units. Then we elaborate on electronic and opto-electronic implementations of the concept. Next to evaluating their performance for standard benchmarks, we also study task independent properties of the system, extracting information on how to further improve the initial scheme. Finally, some simple modifications are suggested, yielding improvements in terms of speed or performance
dc.format	application/pdf
dc.language	eng
dc.publisher	Universitat de les Illes Balears
dc.relation	Tesis doctorals de la UIB
dc.rights	all rights reserved
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	Reservoir computing, delayed feedback systems, machine learning
dc.title	Reservoir computing based on delay-dynamical systems
dc.type	info:eu-repo/semantics/doctoralThesis
dc.type	info:eu-repo/semantics/publishedVersion
dc.doctorat	Doctorat en Física (extingit)