Title :
Semantic phase transition in a classifier based on an adaptive fuzzy system
Author :
Casalino, F. ; Masulli, F. ; Sperduti, A. ; Vannucci, F.
Author_Institution :
Dept. of Comput. & Inf. Sci., Genoa Univ., Italy
Abstract :
We investigate how many rules a particular adaptive fuzzy system, very similar to a feedforward neural network, needs to perform digit classification. Both training of systems with different numbers of fuzzy rules and the application of a pruning technique to a non minimal system support the statement that one rule for each class is needed. In particular, a semantic phase transition is observed when a new rule is added to a system with 9 rules. This behaviour, which is not common for a feedforward neural network, could be ascribed to the derivation of the studied system from a fuzzy logic framework
Keywords :
adaptive systems; character recognition; feedforward neural nets; fuzzy logic; fuzzy systems; pattern classification; adaptive fuzzy system; classifier; digit classification; feedforward neural network; fuzzy logic framework; fuzzy rules; non minimal system; pruning technique; semantic phase transition; Adaptive systems; Computer science; Feedforward neural networks; Feedforward systems; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Neural networks; Physics; Process control;
Conference_Titel :
Fuzzy Systems, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the Third IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1896-X
DOI :
10.1109/FUZZY.1994.343839
