On the Relationship Between Generalization Error, Hypothesis Complexity, and Sample Complexity for Radial Basis Functions

Abstract

In this paper, we bound the generalization error of a class of Radial Basis Function networks, for certain well defined function learning tasks, in terms of the number of parameters and number of examples. We show that the total generalization error is partly due to the insufficient representational capacity of the network (because of its finite size) and partly due to insufficient information about the target function (because of finite number of samples). We make several observations about generalization error which are valid irrespective of the approximation scheme. Our result also sheds light on ways to choose an appropriate network architecture for a particular problem.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1994
Accession Number
ADA276802

Entities

People

  • Federico Girosi
  • Partha Niyogi

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Applied Mathematics
  • Artificial Intelligence
  • Cognitive Science
  • Computer Science
  • Computing System Architectures
  • Convergence
  • Information Processing
  • Network Architecture
  • Neural Networks
  • Probability
  • Probability Distributions
  • Random Variables
  • Statistics
  • Stochastic Processes
  • Theorems
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Regression Analysis.
  • Theoretical Analysis.