Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A neural network approach to real-time pattern recognition
Autore:
Ma, JW;
Indirizzi:
Peking Univ, Sch Math Sci, Dept Informat Sci, Beijing 100871, Peoples R China Peking Univ Beijing Peoples R China 100871 ijing 100871, Peoples R China
Titolo Testata:
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
fascicolo: 6, volume: 15, anno: 2001,
pagine: 937 - 947
SICI:
0218-0014(200109)15:6<937:ANNATR>2.0.ZU;2-A
Fonte:
ISI
Lingua:
ENG
Soggetto:
GENERALIZED HOPFIELD NETWORKS; ASSOCIATIVE MEMORY;
Keywords:
forward neural network; binary neuron; pattern recognition; real-time system; radius of attraction;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
12
Recensione:
Indirizzi per estratti:
Indirizzo: Ma, JW Peking Univ, Sch Math Sci, Dept Informat Sci, Beijing 100871, Peoples R China Peking Univ Beijing Peoples R China 100871 00871, Peoples R China
Citazione:
J.W. Ma, "A neural network approach to real-time pattern recognition", INT J PATT, 15(6), 2001, pp. 937-947

Abstract

This paper presents a new neural network approach to real-time pattern recognition on a given set of binary (or bipolar) sample patterns. The perceptive neuron of a binary pattern is defined and constructed as a binary neuron with a neighborhood perceptive field. Letting its hidden units be the respective perceptive neurons of the patterns, a three-layer forward neural network is constructed to recognize these patterns with minimum error probability in a noisy environment. The theoretical and simulation analyses show that the network is effective for pattern recognition and can be easily implemented under strict real-time constraints.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 04/07/20 alle ore 17:25:58