Study of a New Neuron
classification
adap-org
nlin.AOq-bio
keywords
neuronmodularstandardalternativealthoughanalogarisesback-propagation
read the original 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 $XOR$ 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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.