Robust RBF Finite Automata

Number of the records: 1

1.

SYSNO ASEP	0108848
Document Type	J - Journal Article
R&D Document Type	Journal Article
Subsidiary J	Článek ve WOS
Title	Robust RBF Finite Automata
Title	Robustní RBF konečné automaty
Author(s)	Šorel, Michal (UTIA-B)_{RID, ORCID} Šíma, Jiří (UIVT-O)_{RID, SAI, ORCID}
Source Title	Neurocomputing. - : Elsevier - ISSN 0925-2312 Roč. 62, - (2004), s. 93-110
Number of pages	18 s.
Language	eng - English
Country	NL - Netherlands
Keywords	radial basis function ; neural network ; finite automaton ; Boolean circuit ; computational power
Subject RIV	BA - General Mathematics
R&D Projects	IAB2030007 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR)
	LN00A056 GA MŠMT - Ministry of Education, Youth and Sports (MEYS)
UT WOS	000225681000006
EID SCOPUS	8744285897
DOI	10.1016/j.neucom.2003.12.005
Annotation	The computational power of recurrent RBF(radial basis functions) networks is investigated.A recurrent network which consists of O(sqrt(m logm)) RBF units with maximum norm employing any activation function that has different values in at least two nonnegative points,is constructed so as to implement a given deterministic finite automaton with m states.The underlying simulation proves to be robust with regard to analog noise for a large class of smooth activation functions with a special type of inflections.
Workplace	Institute of Computer Science
Contact	Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800
Year of Publishing	2005

Number of the records: 1