Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Learning object representations using a priori constraints within ORASSYLL
Autore:
Kruger, N;
Indirizzi:
Ruhr Univ Bochum, Inst Neuroinformat, D-44780 Bochum, Germany Ruhr Univ Bochum Bochum Germany D-44780 nformat, D-44780 Bochum, Germany
Titolo Testata:
NEURAL COMPUTATION
fascicolo: 2, volume: 13, anno: 2001,
pagine: 389 - 410
SICI:
0899-7667(200102)13:2<389:LORUAP>2.0.ZU;2-A
Fonte:
ISI
Lingua:
ENG
Soggetto:
VISUAL EXPERIENCE; FACE RECOGNITION; ALGORITHM; RESPONSES; BRAIN; MAPS;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Engineering, Computing & Technology
Citazioni:
46
Recensione:
Indirizzi per estratti:
Indirizzo: Kruger, N Univ Kiel, Inst Informat, D-24105 Kiel, Germany Univ Kiel KielGermany D-24105 Informat, D-24105 Kiel, Germany
Citazione:
N. Kruger, "Learning object representations using a priori constraints within ORASSYLL", NEURAL COMP, 13(2), 2001, pp. 389-410

Abstract

In this article, a biologically plausible and efficient object recognitionsystem (called ORASSYLL) is introduced, based on a set of a priori constraints motivated by findings of developmental psychology and neurophysiology. These constraints are concerned with the organization of the input in local and corresponding entities, the interpretation of the input by its transformation in a highly structured feature space, and the evaluation of features extracted from an image sequence by statistical evaluation criteria. In the context of the bias-variance dilemma, the functional role of a priori knowledge within ORASSYLL is discussed. In contrast to systems in which object representations are defined manually, the introduced constraints allow an autonomous learning from complex scenes.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 19/01/20 alle ore 00:35:38