Title :
NEFCLASS for Java-new learning algorithms
Author :
Nauck, Detlef ; Nauck, Ulrike ; Kruse, Rudolf
Author_Institution :
Fac. of Comput. Sci., Magdeburg Univ., Germany
Abstract :
Neuro-fuzzy classification approaches aim at creating fuzzy classification rules from data. Our neuro-fuzzy model NEFCLASS is able to learn fuzzy rules and fuzzy sets by simple heuristics. The aim of NEFCLASS is to quickly create interpretable fuzzy classifiers. In this paper, we present NEFCLASS-J-a new version of our approach that was written in Java and contains some additions to the learning algorithms, like the treatment of missing values, the ability to use symbolic data, automatic determination of the size of the rule base, and a new automatic pruning strategy
Keywords :
Java; fuzzy logic; fuzzy neural nets; fuzzy set theory; learning (artificial intelligence); pattern classification; Java; NEFCLASS-J; automatic pruning strategy; automatic rule-base size determination; fuzzy classification rules; fuzzy rule learning; fuzzy set learning; heuristics; interpretable fuzzy classifiers; learning algorithms; missing values; neuro-fuzzy classification model; rule number determination; symbolic data; Backpropagation algorithms; Computer science; Electronic mail; Fuzzy sets; Java; Partitioning algorithms; Training data; World Wide Web;
Conference_Titel :
Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American
Conference_Location :
New York, NY
Print_ISBN :
0-7803-5211-4
DOI :
10.1109/NAFIPS.1999.781738
