Study of a New Neuron
adap-org
2008-02-03 v1 Adaptation and Self-Organizing Systems
q-bio
Abstract
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 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.
Cite
@article{arxiv.adap-org/9406001,
title = {Study of a New Neuron},
author = {S. L. Adler and G. V. Bhanot and J. D. Weckel},
journal= {arXiv preprint arXiv:adap-org/9406001},
year = {2008}
}
Comments
19 pages, 7 figures(not included) available upon request, postscript file