Artificial neural network architectures are systems which usually exhibit a unique/special behavior on the basis of a fixed structure expressed in terms of parameters computed by a training phase. In contrast with this approach, we present a robotic scenario in which an artificial neural network architecture, the Multiple Behavior Network (MBN), is proposed as a robotic controller in a simulated environment. MBN is composed of two Continuous-Time Recurrent Neural Networks (CTRNNs), and is organized in a hierarchial way: Interpreter Module ( IM ) and Program Module ( PM ). IM is a fixed-weight CTRNN designed in such a way to behave as an interpreter of the signals coming from PM , thus being able to switch among different behaviors in response to the PM output programs . We suggest how such an MBN architecture can be incrementally trained in order to show and even acquire new behaviors by letting PM learn new programs, and without modifying IM structure.

A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors / Montone, Guglielmo; Donnarumma, Francesco; Prevete, Roberto. - 6593:(2011), pp. 250-259.

A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors

MONTONE, GUGLIELMO;DONNARUMMA, FRANCESCO;PREVETE, ROBERTO
2011

Abstract

Artificial neural network architectures are systems which usually exhibit a unique/special behavior on the basis of a fixed structure expressed in terms of parameters computed by a training phase. In contrast with this approach, we present a robotic scenario in which an artificial neural network architecture, the Multiple Behavior Network (MBN), is proposed as a robotic controller in a simulated environment. MBN is composed of two Continuous-Time Recurrent Neural Networks (CTRNNs), and is organized in a hierarchial way: Interpreter Module ( IM ) and Program Module ( PM ). IM is a fixed-weight CTRNN designed in such a way to behave as an interpreter of the signals coming from PM , thus being able to switch among different behaviors in response to the PM output programs . We suggest how such an MBN architecture can be incrementally trained in order to show and even acquire new behaviors by letting PM learn new programs, and without modifying IM structure.
2011
9783642202810
A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors / Montone, Guglielmo; Donnarumma, Francesco; Prevete, Roberto. - 6593:(2011), pp. 250-259.
File in questo prodotto:
File Dimensione Formato  
multiple_ICANNGA_definitivo_3.pdf

solo utenti autorizzati

Descrizione: Articolo Principale
Tipologia: Documento in Pre-print
Licenza: Accesso privato/ristretto
Dimensione 398.11 kB
Formato Adobe PDF
398.11 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/417220
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact