PARALLEL SELF-ORGANIZING FEATURE MAPS FOR UNSUPERVISED PATTERN RECOGNITION

Abstract

Neural network research has recently undergone a revival for use in pattern recognition applications.¹ If a training set of data can be provided, the supervised types of networks, such as the Hopfield nets or perceptrons, can be used to recognize patterns. ^10·11·18 For unsupervised pattern recognition, systems such as those of the Carpenter/Grossberg ART2 system⁸ and Kohonens’ self-organizing feature maps¹¹ are the most commonly used The problem of poor separability of input vectors was recently addressed by Keller and Hunt with the fuzzy perceptron model. ¹³ However, with the exception of the ART2 system, none of these systems are capable of producing continuous valued output, as would be a desirable model for representation of non-distinct input vectors. This paper presents four new algorithms based on the Kohonen self-organizing feature maps which are capable of generating a continuous valued output. ⁴ We also present the results of some experimental studies run on the NCUBE/10 hypercube at the University of South Carolina.