Simplified ART: A New Class of ART Algorithms

TitleSimplified ART: A New Class of ART Algorithms
Publication TypeTechnical Report
Year of Publication1998
AuthorsBaraldi, A., & Alpaydin E.
Other Numbers1126
KeywordsART 1-based systems, cluster detection, fuzzy clustering, fuzzy set theory, hard and soft competitive learning, Neural Gas algorithm, Self-Organizing Map

The Simplified Adaptive Resonance Theory (SART) class of networks is pro posed to handle problems encountered in Adaptive Resonance Theory 1 (ART 1)-based algorithms when detection of binary and analog patterns is performed. The basic idea of SART is to substitute ART 1-based "unidirectional" (asymmetric) activation and match functions with "bidirectional" (symmetric) function pairs. This substitution makes the class of SART algorithms potentially more robust and less time-consuming than ART 1-based systems. One SART algorithm, termed Fuzzy SART, is discussed. Fuzzy SART employs probabilistic and possibilistic fuzzy membership functions to combine soft competitive learning with outlier detection. Its soft competitive strategy relates Fuzzy SART to the well-known Self-Organizing Map and Neural Gas clustering algorithm. A new Normalized Vector Distance, which can be employed by Fuzzy SART, is also presented. Fuzzy SART performs better than ART 1-based Carpenter-Grossberg-Rosen Fuzzy ART in the clustering of a simple two-dimensional data set and the standard four-dimensional IRIS data set. As expected, Fuzzy SART is less sensitive than Fuzzy ART to small changes in input parameters and in the order of the presentation sequence. In the clustering of the IRIS data set, performances of Fuzzy SART are analogous to or better than those of several clustering models found in the literature.

Bibliographic Notes

ICSI Technical Report TR-98-004

Abbreviated Authors

A. Baraldi and E. Alpaydin

ICSI Publication Type

Technical Report