Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
TOWARDS THE IDEAL SOLUTION IN A LEARNING-PROBLEM WITH DIFFERENT T-NORM OPERATORS
Autore:
NARAZAKI H; RALESCU AL;
Indirizzi:
LAB INT FUZZY ENGN,SIBER HEGNER BLDG 3F,89-1 YAMASHITA CHO,NAKA KU YOKOHAMA 231 JAPAN LAB INT FUZZY ENGN,SIBER HEGNER BLDG 3F,89-1 YAMASHITA CHO,NAKA KU YOKOHAMA 231 JAPAN TOKYO INST TECHNOL,DEPT SYST SCI,LIFE CHAIR FUZZY THEORY,MIDORI KU YOKOHAMA KANAGAWA 227 JAPAN
Titolo Testata:
Fuzzy sets and systems
fascicolo: 1, volume: 56, anno: 1993,
pagine: 51 - 65
SICI:
0165-0114(1993)56:1<51:TTISIA>2.0.ZU;2-6
Fonte:
ISI
Lingua:
ENG
Soggetto:
FUZZY-SETS; LOGIC; CONNECTIVES;
Keywords:
T-NORM; MACHINE LEARNING; MULTIOBJECTIVE DECISION MAKING;
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
Citazioni:
23
Recensione:
Indirizzi per estratti:
Citazione:
H. Narazaki e A.L. Ralescu, "TOWARDS THE IDEAL SOLUTION IN A LEARNING-PROBLEM WITH DIFFERENT T-NORM OPERATORS", Fuzzy sets and systems, 56(1), 1993, pp. 51-65

Abstract

The 'ideal' solution of a learning problem is discussed. Our learningproblem is that of finding p in p --> q with a given data sequence ofq, written as {q(i), i = 1, 2,..., N}. Based on the concept of Zadeh's 'relative sigma-count', we formulate the problem as a multi-objective optimization with 'sufficiency' and 'necessity' criteria. We give explicit formulae of the ideal evidence sequence {p(i)} and we analyze how the ideal sequence depends on different T-norm operations and the parameters specified in the criteria using Schweizer and Sklar's one parameter family of T-norms.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 16/07/20 alle ore 05:22:32