Quantum learning for neural associative memories

Rigatos, GG; Tzafestas, SG

dc.contributor.author	Rigatos, GG	en
dc.contributor.author	Tzafestas, SG	en
dc.date.accessioned	2014-03-01T01:24:57Z
dc.date.available	2014-03-01T01:24:57Z
dc.date.issued	2006	en
dc.identifier.issn	0165-0114	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17510
dc.subject	Associative memories	en
dc.subject	Eigenstructure analysis	en
dc.subject	Hebbian learning	en
dc.subject	Quantum learning	en
dc.subject	Strong fuzzy partition	en
dc.subject	Unitary rotations	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.classification	Mathematics, Applied	en
dc.subject.classification	Statistics & Probability	en
dc.subject.other	Fuzzy control	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Quantum theory	en
dc.subject.other	Vector quantization	en
dc.subject.other	Associative memories	en
dc.subject.other	Eigenstructure analysis	en
dc.subject.other	Hebbian learning	en
dc.subject.other	Quantum learning	en
dc.subject.other	Strong fuzzy partition	en
dc.subject.other	Unitary rotations	en
dc.subject.other	Data processing	en
dc.title	Quantum learning for neural associative memories	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.fss.2006.02.012	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.fss.2006.02.012	en
heal.language	English	en
heal.publicationDate	2006	en
heal.abstract	Quantum information processing in neural structures results in an exponential increase of patterns storage capacity and can explain the extensive memorization and inferencing capabilities of humans. An example can be found in neural associative memories if the synaptic weights are taken to be fuzzy variables. In that case, the weights' update is carried out with the use of a fuzzy learning algorithm which satisfies basic postulates of quantum mechanics. The resulting weight matrix can be decomposed into a superposition of associative memories. Thus, the fundamental memory patterns (attractors) can be mapped into different vector spaces which are related to each other via unitary rotations. Quantum learning increases the storage capacity of associative memories by a factor of 2(N), where N is the number of neurons. (C) 2006 Elsevier B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Fuzzy Sets and Systems	en
dc.identifier.doi	10.1016/j.fss.2006.02.012	en
dc.identifier.isi	ISI:000238402100005	en
dc.identifier.volume	157	en
dc.identifier.issue	13	en
dc.identifier.spage	1797	en
dc.identifier.epage	1813	en