Improving Neural Network Classification Training

The following work presents a new set of general methods for improving neural network accuracy on classification tasks, grouped under the label of classification-based methods. The central theme of these approaches is to provide problem representations and error functions that more directly improve...

Full description

Bibliographic Details
Main Author: Rimer, Michael Edwin
Format: Others
Published: BYU ScholarsArchive 2007
Subjects:
Online Access:https://scholarsarchive.byu.edu/etd/1194
https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=2193&context=etd