Study of a New Neuron
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Description
We study a modular neuron alternative to the McCulloch-Pitts neuron that arises naturally in analog devices in which the neuron inputs are represented as coherent oscillatory wave signals. Although the modular neuron can compute $XOR$ at the one neuron level, it is still characterized by the same Vapnik-Chervonenkis dimension as the standard neuron. We give the formulas needed for constructing networks using the new neuron and training them using back-propagation. A numerical study of the modular neuron on two data sets is presented, which demonstrates that the new neuron performs at least as well as the standard neuron.
19 pages, 7 figures(not included) available upon request, postscript file
19 pages, 7 figures(not included) available upon request, postscript file