Target behaviours can be achieved by finding suitable parameters for Continuous Time Recurrent Neural Networks (CTRNNs) used as agent control systems. Differential Evolution (DE) has been deployed to search parameter space of CTRNNs and overcome granularity, boundedness and blocking limitations. In this paper we provide initial support for DE in the context of two sample learning problems.
CTRNN parameter learning using Differential Evolution / DE FALCO, Ivan; DELLA CIOPPA, Andrea; Donnarumma, Francesco; Maisto, D; Prevete, Roberto; Tarantino, E.. - STAMPA. - 178:(2008), pp. 783-784. (Intervento presentato al convegno Proceeding of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence tenutosi a Kitakyushu, Japan nel November 13-16, 2007) [10.3233/978-1-58603-891-5-783].
CTRNN parameter learning using Differential Evolution
PREVETE, ROBERTO;
2008
Abstract
Target behaviours can be achieved by finding suitable parameters for Continuous Time Recurrent Neural Networks (CTRNNs) used as agent control systems. Differential Evolution (DE) has been deployed to search parameter space of CTRNNs and overcome granularity, boundedness and blocking limitations. In this paper we provide initial support for DE in the context of two sample learning problems.File | Dimensione | Formato | |
---|---|---|---|
CTRNN_Parameter_Learning_using_Different.pdf
non disponibili
Descrizione: Articolo Principale
Tipologia:
Documento in Post-print
Licenza:
Accesso privato/ristretto
Dimensione
241.31 kB
Formato
Adobe PDF
|
241.31 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.