Title :
A guaranteed training of binary pattern mappings using Gaussian perceptron networks
Author_Institution :
Dept. of Comput. Eng., Minnesota Univ., Duluth, MN, USA
Abstract :
Training algorithms are introduced for single- and multiple-layered networks of Gaussian perceptrons. One characteristic of these algorithms is that they can guarantee that a network structure and the corresponding weights will be found for any arbitrarily given mapping relation of binary patterns. A number of computer simulation results are presented to demonstrate the performance of the proposed algorithms
Keywords :
feedforward neural nets; learning (artificial intelligence); pattern recognition; Gaussian perceptron networks; binary pattern mappings; computer simulation; guaranteed training; network structure; performance; Backpropagation algorithms; Computer networks; Computer simulation; Feedforward neural networks; Feedforward systems; Neural networks; Neurons; Proposals; Supervised learning; Vectors;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227106
