RESEARCH COMMONS
LIBRARY

Analysis And Improvement Of Multiple Optimal Learning Factors For Feed-forward Networks

ResearchCommons/Manakin Repository

Analysis And Improvement Of Multiple Optimal Learning Factors For Feed-forward Networks

Show full item record

Title: Analysis And Improvement Of Multiple Optimal Learning Factors For Feed-forward Networks
Author: Jesudhas, Praveen
Abstract: The effects of transforming the net function vector in the Multilayer Perceptron (MLP) are analyzed. The use of optimal diagonal transformation matrices on the net function vector is proved to be equivalent to training the MLP using multiple optimal learning factors (MOLF). A method for linearly compressing large ill-conditioned MOLF Hessian matrices into smaller well-conditioned ones is developed. This compression approach is shown to be equivalent to using several hidden units per learning factor. The technique is extended to large networks. In simulations, the proposed algorithm performs almost as well as the Levenberg Marquardt (LM) algorithm with the computational complexity of a first order training algorithm.
URI: http://hdl.handle.net/10106/5476
Date: 2011-03-03

Files in this item

Files Size Format View
Jesudhas_uta_2502M_10915.pdf 380.8Kb PDF View/Open
PPT_Final.ppt 2.133Mb Microsoft PowerPoint View/Open

This item appears in the following Collection(s)

Show full item record

Browse

My Account

Statistics

About Us