Title :
Neural network design using Voronoi diagrams
Author :
Bose, N.K. ; Garga, Amulya K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Pennsylvania State Univ., University Park, PA, USA
fDate :
9/1/1993 12:00:00 AM
Abstract :
A novel approach is proposed which determines the number of layers, the number of neurons in each layer, and their connection weights for a particular implementation of a neural network, with the multilayer feedforward topology, designed to classify patterns in the multidimensional feature space. The approach is based on construction of a Voronoi diagram over the set of points representing patterns in feature space and this finds added usefulness in deriving alternate neural network structures for realizing the desired pattern classification
Keywords :
computational geometry; feedforward neural nets; pattern recognition; topology; Voronoi diagrams; connection weights; design; multidimensional feature space; multilayer feedforward topology; neural network; pattern classification; Artificial neural networks; Feedforward neural networks; Iterative algorithms; Multi-layer neural network; Multidimensional systems; Network topology; Neural networks; Neurons; Pattern classification; Systems engineering and theory;
Journal_Title :
Neural Networks, IEEE Transactions on
