Memory Capacity of a Random Neural Network
Neural and Evolutionary Computing
2012-11-16 v1
Abstract
This paper considers the problem of information capacity of a random neural network. The network is represented by matrices that are square and symmetrical. The matrices have a weight which determines the highest and lowest possible value found in the matrix. The examined matrices are randomly generated and analyzed by a computer program. We find the surprising result that the capacity of the network is a maximum for the binary random neural network and it does not change as the number of quantization levels associated with the weights increases.
Cite
@article{arxiv.1211.3451,
title = {Memory Capacity of a Random Neural Network},
author = {Matt Stowe},
journal= {arXiv preprint arXiv:1211.3451},
year = {2012}
}
Comments
5 pages, 2 figures