Behavior and Learning in Networks with Differing Amounts of Structure

Abstract

This research is investigating how well large networks that are built from neuron-like elements can be made to perform, and learn to perform, by giving them different types and amounts of built in structure, and the ability to learn by generating new nodes in additions to changing weights. Substantial improvements in both learning speed and performance have been achieved on both pattern recognition problems and a range of problems typically used to demonstrate the power of connectionist networks. In addition, a number of new micro-circuits and sub-networks have been specified with which more powerful and more flexible networks can be built. These include: Back-cycling nets that handle learning(along with many useful functions), rather than have that handled by the system that executes the net; Nets that handle symbols as well as numbers; and Micro-circuits for productions and perceptual transforms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 09, 1991
Accession Number
ADA244080

Entities

People

  • Leonard Uhr

Organizations

  • University of Wisconsin Madison Department of Computer Science

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Automata
  • Coding
  • Computer Languages
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Computers
  • Contrast
  • Detectors
  • Gray Scale
  • Machine Perception
  • Pattern Recognition
  • Recognition
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Science.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks