HEURISTIC AND OPTIMIZATION APPROACHES TO EXTENDING THE KOHONEN SELF-ORGANIZING ALGORITHM

The Kohonen self organizing neural network has been applied to an incr easingly wider range of application problems that traditionally have b een the domain of statistical and operational research techniques, suc h as data clustering and classification, and optimization and control. This Kohonen network is bestowed with a number of unique strengths wh ich are, unfortunately, matched by an equally formidable set of limita tions due its learning algorithm. There have been extensive studies ov er the last decade to extend the Kohonen neural network using heuristi c and optimization approaches. This paper provides a comprehensive sur vey of the research efforts directed to enhancing the Kohonen self org anizing neural network and its learning algorithm. We also point out s ome research directions for pursuing further improvements.