A new model of artificial neuron: cyberneuron and its use
Neural and Evolutionary Computing
2009-07-02 v1 Machine Learning
Abstract
This article describes a new type of artificial neuron, called the authors "cyberneuron". Unlike classical models of artificial neurons, this type of neuron used table substitution instead of the operation of multiplication of input values for the weights. This allowed to significantly increase the information capacity of a single neuron, but also greatly simplify the process of learning. Considered an example of the use of "cyberneuron" with the task of detecting computer viruses.
Keywords
Cite
@article{arxiv.0907.0229,
title = {A new model of artificial neuron: cyberneuron and its use},
author = {S. V. Polikarpov and V. S. Dergachev and K. E. Rumyantsev and D. M. Golubchikov},
journal= {arXiv preprint arXiv:0907.0229},
year = {2009}
}
Comments
23 pages, 23 figures, in Russian