Application-driven parameter tuning methodology for dynamic neural field equations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Application-driven parameter tuning methodology for dynamic neural field equations

Lucian Alecu
Hervé Frezza-Buet

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.

Dates et versions

hal-00439332 , version 1 (07-12-2009)

Identifiants

Citer

Lucian Alecu, Hervé Frezza-Buet. Application-driven parameter tuning methodology for dynamic neural field equations. 16th International Conference on Neural Information Processing - ICONIP 2009, Dec 2009, Bangkok, Thailand. pp.135-142, ⟨10.1007/978-3-642-10677-4_15⟩. ⟨hal-00439332⟩
93 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More