Learn Probability Distributions with The Contrastive Hebbian Algorithm. The Artificial Intelligence and Psychology Project

Abstract

This paper presents a method for training connectional networks that adhere to the principles of graded, random, adaptive, and interactive propagation of information (GRAIN). While our analysis has bee motivated by our desire to find a learning algorithm that would work in this environment, we have succeeded in implementing a model that encompasses a large class of previous connectionist algorithms under the same theoretical principles and that expands the scope of problems they can learn. Stimulations show examples where GRAIN networks successfully approximate both discrete and continuous probability distributions, demonstrating that their scope extends beyond what can be learned by backpropagation networks or standard Boltzmann machines.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 09, 1991
Accession Number
ADA242210

Entities

People

  • J. R. Movellan
  • James McClelland

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Computer Science
  • Equations
  • Gaussian Noise
  • Information Science
  • Neural Networks
  • Order Statistics
  • Probability
  • Probability Distributions
  • Psychology
  • Random Variables
  • Security
  • Simulations
  • Statistical Mechanics
  • Statistics
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks