Constrained topological mapping for nonparametric regression analysis (original) (raw)

The idea 0~' using Kohonen's self-organizing maps is applied to the problem of nonparametric regression attalysis, that is, evaluation (approximation) q [ the unknown .¢~mction of N-I variables given a number of data points (possibly corrupted by random noise) in N-dimensional input space. Simple examples show that the original Kohonen's algorithm perJbrms poorly/or regression problems of even low dimensionalitv, due to the ['act that topologically correct ordering o( units in N-dimensional space may violate the natural topological ordering