Controlling Search Dynamics by Manipulating Energy Landscapes

Abstract

Touretzky and Hinton's DCPS (Distributed Connectionist Production System) is a neural network with complex dynamical properties. Visualization of the energy landscapes of some of its component modules leads to a better intuitive understanding of the model. Three visualization techniques are used in this paper. Analysis of the way energy landscapes change as modules interact during an annealing search suggests ways in which the search dynamics can be controlled, thereby improving the model's performance on difficult match cases. (jes)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1989
Accession Number
ADA225719

Entities

People

  • David S. Touretzky

Organizations

  • Carnegie Mellon University

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Classification
  • Cognitive Science
  • Computer Science
  • Computers
  • Energy Gaps
  • Information Systems
  • Learning
  • Monitoring
  • Neural Networks
  • New York
  • Phase Transformations
  • Probability
  • Psychology
  • Self Organizing Systems
  • United States
  • Universities

Readers

  • Canine Service Warrior Training Program for Wounded Warriors in the Veterinary Industry, Supported by Donors.
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks