Title :
Gaussian perceptron: experimental results
Author_Institution :
Dept. of Comput. Eng., Minnesota Univ., Duluth, MN, USA
Abstract :
A new neural model which has a Gaussian activation function is presented. This model is referred to as the Gaussian perceptron. For the training of single-layered Gaussian perceptrons, the Gaussian perceptron learning algorithm, which is a variant of the conventional perceptron learning algorithm, is presented. The winner-take-all algorithm is proposed as a multilayer training algorithm. A number of examples are presented along with the comparison with backpropagation networks, which demonstrate the performance of Gaussian perceptron networks
Keywords :
learning systems; neural nets; parallel algorithms; Gaussian activation function; Gaussian perceptron learning algorithm; Gaussian perceptron networks; learning systems; multilayer training algorithm; neural nets; winner-take-all algorithm; Associative memory; Backpropagation algorithms; Computer networks; Convergence; Employment; Multi-layer neural network; Nearest neighbor searches; Neural networks; Neurons; Vectors;
Conference_Titel :
Systems, Man, and Cybernetics, 1991. 'Decision Aiding for Complex Systems, Conference Proceedings., 1991 IEEE International Conference on
Conference_Location :
Charlottesville, VA
Print_ISBN :
0-7803-0233-8
DOI :
10.1109/ICSMC.1991.169917
