NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Collections About News Help Login
Back to Results
Training product unit neural networks with genetic algorithmsThe training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.
Document ID
19940013881
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Janson, D. J. (Idaho Univ. Moscow, ID, United States)
Frenzel, J. F. (Idaho Univ. Moscow, ID, United States)
Thelen, D. C. (Idaho Univ. Moscow, ID, United States)
Date Acquired
September 6, 2013
Publication Date
January 1, 1991
Publication Information
Publication: The 1991 3rd NASA Symposium on VLSI Design
Subject Category
Cybernetics
Accession Number
94N18354
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Related Records

IDRelationTitle19940012372Collected WorksFIBER-TEX 1992: The Sixth Conference on Advanced Engineering Fibers and Textile Structures for Composites
No Preview Available