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.
Identifer | oai:union.ndltd.org:UTAHS/oai:digitalcommons.usu.edu:etd-1535 |
Date | 01 May 2010 |
Creators | Bastian, Michael R. |
Publisher | DigitalCommons@USU |
Source Sets | Utah State University |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | All Graduate Theses and Dissertations |
Rights | Copyright for this work is held by the author. Transmission or reproduction of materials protected by copyright beyond that allowed by fair use requires the written permission of the copyright owners. Works not in the public domain cannot be commercially exploited without permission of the copyright owner. Responsibility for any use rests exclusively with the user. For more information contact Andrew Wesolek (andrew.wesolek@usu.edu). |
Page generated in 0.0015 seconds