Connectionist Models: Proceedings of the Summer School Held in San Diego, California on 1990

Abstract

The simplicity and locality of the contrastive Hebb synapse (CHS) used in Boltzmann machine learning makes it an attractive model for real biological synapses. The slow learning exhibited by the stochastic Boltzmann machine can be greatly improved by using a mean field approximation and it has been shown (Hinton, 1989) that the CHS also performs steepest descent in these deterministic mean field networks. A major weakness of the learning procedure, from a biological perspective, is that the derivation assumes detailed symmetry of the connectivity. Using networks with purely asymmetric connectivity, we show that the CHS still works in practice provided the connectivity is grossly symmetrical so that if unit i sends a connection to unit j, there are numerous indirect feedback paths from j to i.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1990
Accession Number
ADA239606

Entities

People

  • David S. Touretzky
  • Geoffrey E. Hinton
  • Jeffrey L. Elman
  • Terrence J. Sejnowski

Organizations

  • University of California, San Diego

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Energy and Power Technologies
  • Engineered Resilient Systems
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Automata Theory
  • Birds
  • Cognitive Science
  • Computational Science
  • Computer Languages
  • Computer Vision
  • Data Mining
  • Dimensionality Reduction
  • Information Processing
  • Information Science
  • Medical Personnel
  • Network Science
  • Neural Networks
  • Psychology
  • Self Organizing Systems
  • Two Dimensional

Readers

  • Calculus or Mathematical Analysis
  • Environmental Impact Assessment (EIA) of Proposed Air Force Base Actions.
  • Neural Network Machine Learning.

Technology Areas

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