Application-Driven Parameter Tuning Methodology for Dynamic Neural Field Equations

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. Key words: dynamic neural field, parameters tuning

• Type: Journal
• Year: 2009
• Where: ICONIP
• Authors: Lucian Alecu, Hervé Frezza-Buet
• Keywords: Dynamic Neural Field, ICONIP 2009, Information Technology, Input Evolution Scenarios, Parameters