Consiglio Nazionale delle Ricerche

Tipo di prodottoAbstract in rivista
TitoloCategory learning through action: A study with human and artificial agents
Anno di pubblicazione2012
Formato-
Autore/iMorlino, Giuseppe; Gianelli, Claudia; Borghi, Anna M.; Nolfi, Stefano
Affiliazioni autoriLARAL-ISTC
Autori CNR e affiliazioni
  • GIUSEPPE MORLINO
  • ANNA MARIA BORGHI
  • STEFANO NOLFI
Lingua/e
  • inglese
AbstractThe abilities to learn to categorize and manipulate new objects are closely related and ubiquitous in cognitive agents. To shed light on the underlying mechanisms and the relationship between these capabilities we designed an experimental comparative scenario in which human and artificial agents were asked to learn to manipulate, through a mouse pointer, unfamiliar two-dimensional objects that varied in shape, color, weight (i.e. inertia to the movement) and color intensity. Objects were grouped on the basis of their characteristic and each group was associated with a different target manipulation. The artificial agents learned through a stochastic trial and error process in which variations to the artificial controller were introduced randomly. The controller, an artificial neural network, received as input the perceptual properties of the object and the current position of the mouse pointer and of the barycenter of the object and determined as output the movement of the mouse pointer. The comparison of the behaviors displayed by human and artificial agents allowed us to identify the role of human cognitive biases, mostly related to visual properties (e.g. shape), that may be beneficial or counterproductive for the acquisition of the task. The analysis of the performances instead showed that both humans and artificial agents used overgeneralized behaviors (i.e. they found and performed manipulations that could be applied to objects belonging to more then one category achieving good, although often sub-optimal, performance) and exploited properties that co-determine the effects of agent/environment interaction (i.e. weight) rather than visual properties.
Pagine das47
Pagine as48
Pagine totali2
RivistaCognitive processing (Print)
Attiva dal 2000
Editore: Springer - Berlin
Paese di pubblicazione: Germania
Lingua: inglese
ISSN: 1612-4782
Titolo chiave: Cognitive processing (Print)
Titolo proprio: Cognitive processing. (Print)
Titolo abbreviato: Cogn. process. (Print)
Numero volume della rivista13
Fascicolo della rivista-
DOI10.1007/s10339-012-0511-7
Verificato da referee-
Stato della pubblicazione-
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:000308824700165)
Parole chiaveEmbodied Cognition, Categorization, Category and Action Learning
Link (URL, URI)http://link.springer.com/journal/10339/13/1/suppl/page/1
Titolo parallelo-
Scadenza embargo-
Licenza-
Data di accettazione-
Note/Altre informazioniID_PUMA: /cnr.istc/2012-A7-009
Strutture CNR
  • ISTC — Istituto di scienze e tecnologie della cognizione
Moduli/Attività/Sottoprogetti CNR
  • ICT.P08.006.001 : Tecnologie avanzate per l'interazione uomo, robot ed agenti intelligenti
Progetti Europei-
Allegati
Category learning through action: A study with human and artificial agents (documento privato )
Tipo documento: application/pdf

Dati associati a vecchie tipologie
I dati associati a vecchie tipologie non sono modificabili, derivano dal cambiamento della tipologia di prodotto e hanno solo valore storico.
Editore
  • Springer, Berlin (Germania)
Lingua abstractinglese