Networks and the Best Approximation Property

Abstract

Networks can be considered as approximation schemes. Multilayer networks of the backpropagation type can approximate arbitrarily well continuous functions (Cybenko, 1989; Funahashi, 1989; Stinchcombe and White, 1989). We prove that networks derived from regularization theory and including Radial Basis functions (Poggio and Girosi, 1989), have a similar property. From the point of view of approximation theory, however, the property of approximation continuous functions arbitrarily well is not sufficient for characterizing good approximation schemes. More critical is the property of best approximation. The main result of this paper is that multilayer networks, of the type used in backpropagation, are not best approximation. For regularization networks (in particular Radial Basis Function networks) we prove existence and uniqueness of best approximation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA216712

Entities

People

  • Federico Girosi
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Advanced Electronics
  • Air Platforms

DTIC Thesaurus Topics

  • Algebra
  • Artificial Intelligence
  • Cognitive Science
  • Contracts
  • Department Of Defense
  • Differential Equations
  • Equations
  • Functional Analysis
  • Information Processing
  • Information Systems
  • Learning
  • Military Research
  • Neural Networks
  • Numbers
  • Polynomials
  • Rational Numbers
  • Real Numbers

Readers

  • Mathematical Modeling and Probability Theory.
  • Neural Network Machine Learning.