Date of Award
12-1-2013
Degree Name
Doctor of Philosophy
Department
Electrical and Computer Engineering
First Advisor
Sayeh, Mohammad
Abstract
The proteretic Hopfield neural network is studied in this work. Hysteresis is a Greek word which means deficiency or lagging behind, and it can be defined as the occurrence of a delayed effect when forces acting on an abject are varied. It will be shown that the proteresis, which is the reverse of hysteresis, can increase the speed of convergence of the Hopfield network. We will make a comparison among the traditional Hopfield, the hysteretic Hopfield, and the proteretic Hopfield. It will be proven that the proteresis is increasing the speed of convergence of the Hopfield associative memory and the Hopfield analog to digital converter without compromising the accuracy.
Access
This dissertation is only available for download to the SIUC community. Current SIUC affiliates may also access this paper off campus by searching Dissertations & Theses @ Southern Illinois University Carbondale from ProQuest. Others should contact the interlibrary loan department of your local library or contact ProQuest's Dissertation Express service.