Date of Award:
5-2010
Document Type:
Dissertation
Degree Name:
Doctor of Philosophy (PhD)
Department:
Electrical and Computer Engineering
Committee Chair(s)
Jacob H. Gunther
Committee
Jacob H. Gunther
Committee
Todd K. Moon
Committee
YangQuan Chen
Committee
Wei Ren
Committee
Donald Cooley
Abstract
Neural network training algorithms have always suffered from the problem of local minima. The advent of natural gradient algorithms promised to overcome this shortcoming by finding better local minima. However, they require additional training parameters and computational overhead. By using a new formulation for the natural gradient, an algorithm is described that uses less memory and processing time than previous algorithms with comparable performance.
Checksum
b6bceb03b4dde605214baecaa99811a9
Recommended Citation
Bastian, Michael R., "Neural Networks and the Natural Gradient" (2010). All Graduate Theses and Dissertations, Spring 1920 to Summer 2023. 539.
https://digitalcommons.usu.edu/etd/539
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .