An unsupervised neural network using a fuzzy learning rule
Yong Soo Kim · 1999
This paper presents a fuzzy neural network which utilizes a similarity measure of the relative distance and a fuzzy learning rule. A fuzzy learning rule consists of a fuzzy membership value, an intra-cluster membership value, and a function of the number of iterations. The proposed fuzzy neural network updates weights of all committed output neurons regardless of winning or losing. The proposed fuzzy neural network is evaluated using the IRIS data set.