Date of Award
1-1-2008
Degree Name
Doctor of Philosophy
Department
Electrical and Computer Engineering
First Advisor
Sayeh, Mohammed
Abstract
The Hopfield neuron with predictive hysteresis is proposed and the efficiency of employing these neurons in analog to digital conversion, via the Hopfield Neural Network, will be demonstrated. Traditional hysteresis is defined, generally, as the occurrence of a delayed effect when forces acting on an object are varied. It will be shown that predictive hysteresis, a type of reverse hysteresis, improves upon the speed of hysteretic and non hysteretic systems without compromising the accuracy.
Access
This dissertation is only
available for download to the SIUC community. Others should contact the
interlibrary loan department of your local library or contact ProQuest's
Dissertation Express service.