Multilayer Networks of Self-Interested Adaptive Units.

Abstract

This report describes research directed toward refining and evaluating learning methods for multilayer networks of neuron-like adaptive units. We define a learning rule called the Associative Reward-Penalty, or A sub R-P, rule that has strong ties to both the theory of adaptive pattern classification and stochastic learning automata. We state a convergence result that has been proven for a single A sub R-P units can reliably learn nonlinear associative mappings. The behavior of these networks is discussed in terms of the collective behavior of stochastic learning automata in team decision problems. A number of methods for learning in multilayer networks are compared, including the A sub R-P method and the error back-propagation method. These methods, or variants of them, outperform the other methods applied to the test problem, with error back-propagation showing a significant speed advantage over the other methods. The A sub R-P and error back-propagation are compared and contrasted in terms of their respective approaches to gradient following.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1987
Accession Number
ADA183782

Entities

People

  • Andrew G. Barto

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Advanced Electronics
  • C4I
  • Cyber

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata
  • Cognitive Science
  • Computational Science
  • Computer Programs
  • Computer Simulations
  • Computers
  • Control Systems
  • Differential Equations
  • Distribution Functions
  • Information Science
  • Neural Networks
  • Probability Density Functions
  • Random Variables
  • Simulations
  • Two Dimensional

Fields of Study

  • Computer science

Readers

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