Fuzzy combination of Kohonen's and ART neural network models to detect statistical regularities in a random sequence of multi-valued input patterns

Abstract

A fuzzy simplified ART (SART) implementation is now proposed to combine SART architecture with a Kohonen-based soft learning strategy which employs a fuzzy membership function. Fuzzy SART consists of an attentional and an orienting subsystem. The fuzzy SART attentional subsystem is a self-organizing feedforward flat homogeneous network performing learning by examples. During the processing of a given data set, the fuzzy SART orienting subsystem: 1) adds a new neuron to the attentional subsystem whenever the system fails to recognize an input pattern; and 2) removes a previously allocated neuron from the attentional subsystem if the neuron is no longer able to categorize any input pattern. The performance of fuzzy SART is compared with that of the CGR fuzzy ART model when a 2D data set and the 4D IRIS data set are processed. Unlike the CGR fuzzy ART system, fuzzy SART: 1) requires no input data preprocessing; 2) features stability to small changes in input parameters and in the order of the input sequence; and 3) is competitive when compared to other neural network models found in the literature.