Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
REORGANIZING KNOWLEDGE IN NEURAL NETWORKS - AN EXPLANATORY MECHANISM FOR NEURAL NETWORKS IN DATA CLASSIFICATION PROBLEMS
Autore:
NARAZAKI H; WATANABE T; YAMAMOTO M;
Indirizzi:
KOBE STEEL LTD,PROC TECHNOL RES LAB KOBE 65122 JAPAN KOBE STEEL LTD,KAKOGAWA WORKS KAKOGAWA HYOGO 675 JAPAN
Titolo Testata:
IEEE transactions on systems, man and cybernetics. Part B. Cybernetics
fascicolo: 1, volume: 26, anno: 1996,
pagine: 107 - 117
SICI:
1083-4419(1996)26:1<107:RKINN->2.0.ZU;2-8
Fonte:
ISI
Lingua:
ENG
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
12
Recensione:
Indirizzi per estratti:
Citazione:
H. Narazaki et al., "REORGANIZING KNOWLEDGE IN NEURAL NETWORKS - AN EXPLANATORY MECHANISM FOR NEURAL NETWORKS IN DATA CLASSIFICATION PROBLEMS", IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, 26(1), 1996, pp. 107-117

Abstract

We propose an explanatory mechanism for multilayered neural networks (NN). In spite of the effective learning capability as a uniform function approximator, the multilayered NN suffers from unreadability, i.e., it is difficult for the user to interpret or understand the ''knowledge'' that the NN has by looking at the connection weights and thresholds obtained by backpropagation (BP). This unreadability comes from the distributed nature of the knowledge representation in the NN. In this paper, we propose a method that reorganizes the distributed knowledge in the NN to extract approximate classification rules. Our rule extraction method is based on the analysis of the function that the NN haslearned, rather than on the direct interpretation of connection weights as correlation information, More specifically, our method divides the input space into ''monotonic regions'' where a monotonic region is a set of input patterns that belongs to the same class with the same sensitivity pattern. Approximate classification rules are generated by projecting these monotonic regions.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 02/07/20 alle ore 22:18:30