Neural network models
Abstract
This work presents the current collection of mathematical models related to neural networks and proposes a new family of such with extended structure and dynamics in order to attain a selection of cognitive capabilities. It starts by providing a basic background to the morphology and physiology of the biological and the foundations and advances of the artificial neural networks. The first part then continues with a survey of all current mathematical models and some of their derived properties. In the second part, a new family of models is formulated, compared with the rest, and developed analytically and numerically. Finally, important additional aspects and any limitations to deal with in the future are discussed.
Cite
@article{arxiv.2301.02987,
title = {Neural network models},
author = {Plamen Dimitrov},
journal= {arXiv preprint arXiv:2301.02987},
year = {2023}
}
Comments
112 pages, 26 figures, master thesis in Mathematics, supervised by Debora Amadori and Leonardo Guidoni, submitted on November 30, 2016