The G\^ateaux-Hopfield Neural Network method
Machine Learning
2020-02-03 v1 Neural and Evolutionary Computing
Abstract
In the present work a new set of differential equations for the Hopfield Neural Network (HNN) method were established by means of the Linear Extended Gateaux Derivative (LEGD). This new approach will be referred to as G\^ateaux-Hopfiel Neural Network (GHNN). A first order Fredholm integral problem was used to test this new method and it was found to converge 22 times faster to the exact solutions for {\alpha} > 1 if compared with the HNN integer order differential equations. Also a limit to the learning time is observed by analysing the results for different values of {\alpha}. The robustness and advantages of this new method will be pointed out.
Keywords
Cite
@article{arxiv.2001.11853,
title = {The G\^ateaux-Hopfield Neural Network method},
author = {Felipe Silva Carvalho and João Pedro Braga},
journal= {arXiv preprint arXiv:2001.11853},
year = {2020}
}
Comments
15 pages, 2 figures