Premium
Error prediction for neural networks by fuzzification
Author(s) -
Feuring Thomas,
Lippe WolframM.
Publication year - 1998
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/(sici)1098-111x(199806)13:6<495::aid-int5>3.0.co;2-g
Subject(s) - neuro fuzzy , artificial neural network , computer science , fuzzy set operations , fuzzy logic , artificial intelligence , fuzzy number , defuzzification , set (abstract data type) , fuzzy set , fuzzy classification , property (philosophy) , adaptive neuro fuzzy inference system , data mining , fuzzy control system , machine learning , philosophy , epistemology , programming language
In classical “crisp” neural networks the output cannot be estimated for arbitrary input data. This situation can be overcome if fuzzy neural nets are trained with fuzzy data. These “continuous” data often better describe certain situations. Because fuzzy neural networks map fuzzy numbers to fuzzy numbers, a criterion for choosing a “good” training set can be formulated. Together with an important fuzzy neural network property, the output for arbitrary crisp input data can be estimated based on the fuzzy training set. © 1998 John Wiley & Sons, Inc.