Actions for Premature saturation in backpropagation networks [electronic resource] : Mechanism and necessary conditions

Email RIS file
Bookmark
Report an Issue

Premature saturation in backpropagation networks [electronic resource] : Mechanism and necessary conditions

Published
Washington, D.C. : United States. Dept. of Energy, 1997.
Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy.
Physical Description
49 pages : digital, PDF file
Additional Creators
Argonne National Laboratory, United States. Department of Energy, and United States. Department of Energy. Office of Scientific and Technical Information
Access Online

Availability

I Want It
I Want It

Finding items...

Restrictions on Access
Free-to-read Unrestricted online access
Summary
The mechanism that gives rise to the phenomenon of premature saturation of the output units of feedforward multilayer neural networks during training with the standard backpropagation algorithm is described. The entire process of premature saturation is characterized by three distinct stages and it is concluded that the momentum term plays the leading role in the occurrence of the phenomenon. The necessary conditions for the occurrence of premature saturation are presented and a new method is proposed, based on these conditions, that eliminates the occurrence of the phenomenon. Validity of the conditions and the proposed method are illustrated through simulation results. Three case studies are presented. The first two came from a training session for classification of three component failures in a nuclear power plant. The last case, comes from a training session for classification of welded fuel elements.
Report Numbers
E 1.99:anl/ra/pp--89239
anl/ra/pp--89239
Subject(s)
Other Subject(s)
Note
Published through SciTech Connect.
08/01/1997.
"anl/ra/pp--89239"
"DE97008122"
Reifman, J.; Vitela, J.E.
Funding Information
W-31109-ENG-38
View MARC record | catkey: 14352565