Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloLearning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario
Anno di pubblicazione2015
FormatoCartaceo
Autore/iFrancesco Donnarumma, Roberto Prevete, Andrea de Giorgio, Guglielmo Montone, Giovanni Pezzulo
Affiliazioni autoriISTC-CNR
Autori CNR e affiliazioni
  • GIOVANNI PEZZULO
Lingua/e
  • inglese
AbstractDistributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a novel proposal, a hierarchical programmable neural network architecture, based on the notion of programmability and an interpreter-programmer computational scheme. In this approach, complex (and novel) behaviors can be acquired by embedding multiple modules (motor primitives) in a single, multi-purpose neural network. This is supported by recent theories of brain functioning in which skilled behaviors can be generated by combining functional different primitives embedded in "reusable" areas of "recycled" neurons. Such neuronal substrate supports flexible cognitive control, too. Modules are seen as interpreters of behaviors having controlling input parameters, or programs that encode structures of networks to be interpreted. Flexible cognitive control can be exerted by a programmer module feeding the interpreters with appropriate input parameters, without modifying connectivity. Our results in a multiple T -maze robotic scenario show how this computational framework provides a robust, scalable and flexible scheme that can be iterated at different hierarchical layers permitting to learn, encode and control multiple qualitatively different behaviors.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali-
RivistaAdaptive behavior
Attiva dal 1992
Editore: MIT Press, - Cambridge, MA
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 1059-7123
Titolo chiave: Adaptive behavior
Titolo proprio: Adaptive behavior.
Titolo abbreviato: Adapt. behav.
Numero volume della rivista-
Fascicolo della rivista-
DOI-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveProgramming neural networks, hierarchical organization, distributed representation, neuronal reuse, cognitive control
Link (URL, URI)-
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISTC — Istituto di scienze e tecnologie della cognizione
Moduli/Attività/Sottoprogetti CNR
  • SV.P16.008.001 : Computational Embodied Neuroscience
Progetti Europei-
Allegati