Connectionist Learning Procedures.

Abstract

A major goal of research on networks of neuron-like processing units is to discover efficient learning procedures that allow these networks to construct complex internal representations of their environment. The learning procedures must be capable of modifying the connection strengths in such a way that internal units which are not part of the input or output come to represent important features of the task domain. Several interesting gradient-descent procedures have recently been discovered. Each connection computes the derivative, with respect to the connection strength, of a global measure of the error in the the performance of the network. The strength is then adjusted in the direction that decrease the error. These relatively simple, gradient-descent learning procedures work well for small tasks and the new challenge is to find ways of improving the speed of learning so that they can be applied to larger, more realistic tasks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 04, 1987
Accession Number
ADA185394

Entities

People

  • Geoffrey E. Hinton

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Cognitive Science
  • Computational Science
  • Computer Languages
  • Computer Science
  • Computer Vision
  • Computers
  • Content Addressable Memory
  • Dimensionality Reduction
  • Information Science
  • Machine Learning
  • Network Science
  • Neural Networks
  • Pattern Recognition
  • Self Organizing Systems

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.