Ecological neural networks for object recognition and generalization (Articolo in rivista)

Type

• Prodotto della ricerca (Classe)
• Articolo in rivista (Classe)

Label

• Ecological neural networks for object recognition and generalization (Articolo in rivista) (literal)

Anno

• 2004-01-01T00:00:00+01:00 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi

• 10.1023/B:NEPL.0000016846.74699.1a (literal)

Alternative label

• Calabretta R.; Di Ferdinando A.; Parisi, D. (2004)
  Ecological neural networks for object recognition and generalization
  in Neural Processing Letters
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• Calabretta R.; Di Ferdinando A.; Parisi, D. (literal)

Pagina inizio

• 37 (literal)

Pagina fine

• 48 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume

• 19 (literal)

Rivista

• Neural Processing Letters (Rivista)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note

• Neural Processing Letters (Kluwer Academic Publisher) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroFascicolo

• 1 (literal)

Note

• ISI Web of Science (WOS) (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• Raffaele Calabretta, Institute of Cognitive Sciences and Technologies National Research Council, Rome, Italy Andrea Di Ferdinando, Institute of Cognitive Sciences and Technologies National Research Council, Rome, Italy and University of Rome “La Sapienza” Rome, Italy Domenico Parisi, Institute of Cognitive Sciences and Technologies National Research Council, Rome, Italy (literal)

Titolo

• Ecological neural networks for object recognition and generalization (literal)

Abstract

• Generalization is a critical capacity for organisms. Modeling the behavior of organisms with neural networks, some type of generalizations appear to be accessible to neural networks but other types do not. In this paper we present two simulations. In the first simulation we show that while neural networks can recognize where an object is located in the retina even if they have never experienced that object in that position (“where” generalization subtask), they have difficulty in recognizing the identity of a familiar object in a new position (”what” generalization subtask). In the second simulation we explore the hypothesis that organisms find another solution to the problem of recognizing objects in different positions on their retina: they move their eyes so that objects are always seen in the same position in the retina. This strategy emerges spontaneously in ecological neural networks that are allowed to move their 'eye' in order to bring different portions of the visible world in the central portion of their retina. (literal)

Prodotto di

• Tecnologie avanzate per l'interazione uomo, robot ed agenti intelligenti (ICT.P08.006.001) (Modulo)
• Institute of cognitive sciences and technologies (ISTC) (Istituto)

Autore CNR

• RAFFAELE CALABRETTA (Unità di personale interno)
• DOMENICO PARISI (Persona)

Insieme di parole chiave

• Parole chiave di "Ecological neural networks for object recognition and generalization" (Insieme di parole chiave)

Incoming links:

Autore CNR di

• RAFFAELE CALABRETTA (Unità di personale interno)
• DOMENICO PARISI (Persona)

Prodotto

• Institute of cognitive sciences and technologies (ISTC) (Istituto)
• Tecnologie avanzate per l'interazione uomo, robot ed agenti intelligenti (ICT.P08.006.001) (Modulo)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi

• Neural Processing Letters (Rivista)

Insieme di parole chiave di

• Parole chiave di "Ecological neural networks for object recognition and generalization" (Insieme di parole chiave)