Template-Type: ReDIF-Paper 1.0
Author-Name: van den Bergh, W.-M.
Author-Name-Last: van den Bergh
Author-Name-First: Willem-Max
Author-Name: van den Berg, J.H.
Author-Name-Last: van den Berg
Author-Name-First: Jan
Title: Competitive exception learning using fuzzy frequency distributions
Abstract: A competitive exception learning algorithm for finding a non-linear mapping is proposed which puts the emphasis on the discovery of the important exceptions rather than the main rules. To do so,we first cluster the output space using a competitive fuzzy clustering algorithm and derive a fuzzy frequency distribution describing the general, average system's output behavior. Next, we look for a fuzzy partitioning of the input space in such away that the corresponding fuzzy output frequency distributions `deviate at most' from the average one as found in the first step. In this way, the most important `exceptional regions' in the input-output relation are determined. Using the joint input-output fuzzy frequency distributions, the complete input-output function as extracted from the data, can be expressed mathematically. In addition, the exceptions encountered can be collected and described as a set of fuzzy if-then-else-rules. Besides presenting a theoretical description of the new exception learning algorithm, we report on the outcomes of certain practical simulations.
Creation-Date: 2000-05-02
File-URL: https://repub.eur.nl/pub/15/erimrs20000502164035.pdf
File-Format: application/pdf
Series: RePEc:ems:eureri
Number: ERS-2000-06-LIS
Classification-JEL: C6, M, M11, R4
Keywords: competitive learning, exception learning, fuzzy pattern recognition
Handle: RePEc:ems:eureri:15