Date of Award:
5-2010
Document Type:
Dissertation
Degree Name:
Doctor of Philosophy (PhD)
Department:
Electrical and Computer Engineering
Advisor/Chair:
Dr. Jacob H. Gunther
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.
Recommended Citation
Bastian, Michael R., "Neural Networks and the Natural Gradient" (2010). All Graduate Theses and Dissertations. Paper 539.
http://digitalcommons.usu.edu/etd/539
Copyright for this work is retained by the student.