Abstract of FKI-199-94

Document-Name:  fki-195-94.ps.gz
Title:          Function Approximation With Continuous-Valued Activation 
                Functions in CMAC
Authors:        Martin Eldracher, Alexander Staller, Rene Pompl 
Revision-Date:  1994/12/15 
Category:       Technical Report (Forschungsberichte Künstliche Intelligenz)
Abstract:       CMAC is well known as a good
		function approximator with local generalization
		abilities. Depending on smoothness of the function to
		be approximated, the resolution as smallest
		distinguishable part of the input domain, plays a
		crucial role. If the usually used binary quantizing
		functions are dropped in favor of more general,
		continuous valued functions, this drawback can be
		remedied. We introduce such a model, using gaussians
		instead of binary functions.  We show the far better
		results in learning two valued functions with this
		continuous valued activation function
Keywords:       function approximation, CMAC, continuos activation functions
                neural network, learning, adaptive input representations,
                data dependend representation
Size:           37 pages
Language:       English
ISSN:           0941-6358
Copyright:      The ``Forschungsberichte Künstliche Intelligenz''
                series includes primarily preliminary publications,
                specialized partial results, and supplementary
                material. In the interest of a subsequent final
                publication these reports should not be copied. All
                rights and the responsability for the contents of the
                report are with the authors, which would appreciate
                critical comments.

Gerhard Weiss