Nanoscale artificial intelligence: creating artificial neural networks using autocatalytic reactions
Adaptation and Self-Organizing Systems
2016-03-01 v1 Emerging Technologies
Abstract
A general methodology is proposed to engineer a system of interacting components (particles) which is able to self-regulate their concentrations in order to produce any prescribed output in response to a particular input. The methodology is based on the mathematical equivalence between artificial neurons in neural networks and species in autocatalytic reactions, and it specifies the relationship between the artificial neural network's parameters and the rate coefficients of the reactions between particle species. Such systems are characterised by a high degree of robustness as they are able to reach the desired output despite disturbances and perturbations of the concentrations of the various species.
Cite
@article{arxiv.1602.09070,
title = {Nanoscale artificial intelligence: creating artificial neural networks using autocatalytic reactions},
author = {Filippo Simini},
journal= {arXiv preprint arXiv:1602.09070},
year = {2016}
}
Comments
15 pages, 3 figures