Semiclassical Neural Network
Quantum Physics
2007-10-11 v3 Disordered Systems and Neural Networks
Artificial Intelligence
q-bio
Abstract
We have constructed a simple semiclassical model of neural network where neurons have quantum links with one another in a chosen way and affect one another in a fashion analogous to action potentials. We have examined the role of stochasticity introduced by the quantum potential and compare the system with the classical system of an integrate-and-fire model by Hopfield. Average periodicity and short term retentivity of input memory are noted.
Cite
@article{arxiv.quant-ph/0202015,
title = {Semiclassical Neural Network},
author = {Fariel Shafee},
journal= {arXiv preprint arXiv:quant-ph/0202015},
year = {2007}
}
Comments
8 pages 2 figures; new sections and figures added on short term memory and period