Application-driven parameter tuning methodology for dynamic neural field equations

Lucian Alecu; Hervé Frezza-Buet

hal-00439332, version 1

Application-driven parameter tuning methodology for dynamic neural field equations

Lucian Alecu () ^1, 2, Hervé Frezza-Buet () ¹

16th International Conference on Neural Information Processing - ICONIP 2009 5863/2009 (2009) 135-142

Résumé : In this paper, a method is introduced in order to qualify the performance of dynamic neural fields (DNF). The method is applied to Amari's DNF equations, in order to drive the tuning of its free parameters. An original evaluation procedure is presented, and then applied to some input evolution scenarios. Such scenarios define an applicative context, for which the parameters with the lowest evaluation are optimal.

1 : SUPELEC-Campus Metz
SUPELEC
2 : CORTEX (INRIA Lorraine - LORIA)
INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)

hal-00439332, version 1
http://hal-supelec.archives-ouvertes.fr/hal-00439332
oai:hal-supelec.archives-ouvertes.fr:hal-00439332
Contributeur : Sébastien Van Luchene <>
Soumis le : Lundi 7 Décembre 2009, 12:26:38
Dernière modification le : Lundi 4 Janvier 2010, 11:45:07

Voir la fiche détaillée

Documents associés

DOI : 10.1007/978-3-642-10677-4_15

Exporter

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Communications avec actes</head>
<biblStruct type="inproceedings" xml:id="hal-00439332"><analytic>
<author><persName><forename>Lucian</forename><surname>Alecu</surname></persName>
<affiliation>
<orgName type="team">SUPELEC-Campus Metz</orgName>
<country>FR</country>
<orgName type="institution">SUPELEC</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Lorraine - LORIA</orgName>
<orgName type="team">CORTEX</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR7503</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>Hervé</forename><surname>Frezza-Buet</surname></persName>
<affiliation>
<orgName type="team">SUPELEC-Campus Metz</orgName>
<country>FR</country>
<orgName type="institution">SUPELEC</orgName>
</affiliation>
</author>
<title type="main" level="a">Application-driven parameter tuning methodology for dynamic neural field equations</title></analytic><monogr><title level="m" type="main">Neural Information Processing, ICONIP'09 Proceedings, Part I</title><meeting>16th International Conference on Neural Information Processing - ICONIP 2009</meeting><imprint><publisher>Springer</publisher><pubPlace><settlement>Bangkok</settlement><country>Thaïlande</country></pubPlace><biblScope type="publicationDate">2009-12-00</biblScope><biblScope type="vol">5863/2009</biblScope><biblScope type="pp">135-142</biblScope></imprint></monogr><idno type="doi">10.1007/978-3-642-10677-4_15</idno><idno type="HALid">http://hal-supelec.archives-ouvertes.fr/hal-00439332</idno></biblStruct>
</listBibl>
</listBibl>