The Open Applied Mathematics Journal

2008, 2 : 31-58
Published online 2008 April 15. DOI: 10.2174/1874114200802010031
Publisher ID: TOAMJ-2-31

Universal Approximation by Ridge Computational Models and Neural Networks:

A. Survey
Department of Communications, Computer and System Sciences (DIST) University of Genova { Via Opera Pia 13, 16145 Genova, Italy.

ABSTRACT

Computational models made up of linear combinations of ridge basis functions, widely used in machine learning and arti¯cial intelligence, are considered. For such models, the literature on the so-called \universal approximation property" is surveyed. Di®erent approaches, proof techniques, and tools are examined.

Keywords:

nonlinear computational models, ridge computational units, universal approximation, Complexity.