A directional weighted backpropagated error used in decision making applications
Loading...
Authors
Srigiriraju, Subhadrakumari K.
Advisors
Skinner, Steven R.
Issue Date
2006-07
Type
Thesis
Keywords
Artificial Neural Networks , Signal processing
Citation
Abstract
A new and unique directional weighted error function was introduced into the backpropagation algorithm used in Artificial Neural Networks (ANNs) for applications where yes or no decisions are made on the output. A continuous error function based on a weighted curve is suggested for use in the backpropagation algorithm in an effort to increase the number of correct decisions. Results were compared to the standard and weighted error methods. A higher number of correct decisions were made with the new method.
Table of Contents
Description
Thesis (M.S.)--Wichita State University, College of Engineering, Dept. of Electrical and Computer Engineering.
"July 2006."
Includes bibliographic references (leaves 36-37).
"July 2006."
Includes bibliographic references (leaves 36-37).