Harmony Theory: Problem Solving, Parallel Cognitive Models, and Thermal Physics.

Abstract

The first paper describes a parallel model designed to solve a class of relatively simple problems from elementary physics, and discusses the implications for models of problem solving in general. The authors show how one of the most salient features of problem solving, sequentiality, can emerge naturally within a parallel model that has no explicit knowledge of how to sequence analysis. This model exploits a new type of parallel distributed processing that employs stochastic processors and is based on a formal mapping between parallel computation and thermal physics. The mathematical theory is this type of processing-harmony theory-is discussed in the second and third papers. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1984
Accession Number
ADA140877

Entities

People

  • M. S. Riley
  • P. Smolensky

Organizations

  • University of California, San Diego

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Cognition
  • Cognitive Science
  • Computational Processes
  • Computations
  • Computers
  • High Temperature
  • Mathematical Analysis
  • Neural Networks
  • Parallel Computing
  • Parallel Processing
  • Pattern Recognition
  • Probability
  • Probability Distributions
  • Resistance
  • Sequence Analysis
  • Sequences

Readers

  • Artificial Intelligence
  • Theoretical Analysis.