Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
ROUGH FUZZY MLP - KNOWLEDGE ENCODING AND CLASSIFICATION
Autore:
BANERJEE M; MITRA S; PAL SK;
Indirizzi:
INDIAN INST TECHNOL,DEPT MATH KANPUR 208016 UTTAR PRADESH INDIA INDIAN STAT INST,MACHINE INTELLIGENCE UNIT CALCUTTA 700035 W BENGAL INDIA
Titolo Testata:
IEEE transactions on neural networks
fascicolo: 6, volume: 9, anno: 1998,
pagine: 1203 - 1216
SICI:
1045-9227(1998)9:6<1203:RFM-KE>2.0.ZU;2-S
Fonte:
ISI
Lingua:
ENG
Soggetto:
MULTILAYER PERCEPTRON; NEURAL NETWORKS; SETS;
Keywords:
FUZZY MLP; KNOWLEDGE-BASED NETWORKS; NETWORK DESIGN; PATTERN RECOGNITION; ROUGH SETS; RULE GENERATION; SOFT COMPUTING; SPEECH RECOGNITION;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
CompuMath Citation Index
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
26
Recensione:
Indirizzi per estratti:
Citazione:
M. Banerjee et al., "ROUGH FUZZY MLP - KNOWLEDGE ENCODING AND CLASSIFICATION", IEEE transactions on neural networks, 9(6), 1998, pp. 1203-1216

Abstract

A new scheme of knowledge encoding in a fuzzy multilayer perceptron (MLP) using rough set-theoretic concepts is described, Crude domain knowledge is extracted from the data set in the form of rules, The syntaxof these rules automatically determines the appropriate number of hidden nodes while the dependency factors are used in the initial weight encoding, The network is then refined during training. Results on classification of speech and synthetic data demonstrate the superiority ofthe system over the Fuzzy and conventional versions of the MLP (involving no initial knowledge).

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 10/07/20 alle ore 12:10:58