A neural network approach to the construction of Delaunay tessellation of points in R/sup d/

Since a neural network may be designed directly from either the Delaunay tessellation (DT) or its abstract dual, the Voronoi diagram, the procedure advanced here for training a dynamic feedforward neural network to generate the DT of specified points representing exemplars in multidimensional feature space, contributes toward the goal of an all-neural approach to the synthesis of neural networks. As the expected number of simplexes in the DT over n points is linear in n, the procedure is convenient for real-time implementation of pattern classifiers. >