Frequency Domain Robustness Analysis of Hopfield and Modified Hopfield Neural Networks

Jie Shen
S. N. Balakrishnan, Missouri University of Science and Technology

This document has been relocated to

There were 2 downloads as of 27 Jun 2016.


A variant of Hopfield neural network, called the modified Hopfield network, is formulated in this study. This class of networks consists of parallel recurrent networks which have variable dimensions that can be changed to fit the problem under consideration. It has a structure to implement an inverse transformation that is essential for embedding optimal control gain sequences. Equilibrium solutions of this network are discussed. The robustness of this network and the classical Hopfield network are carried out in the frequency domain using describing functions