Theory of Neural Networks

Abstract

A new neural unsupervised learning technique has been proposed in this work. Technique is based on the hierarchical partition of the patterns. Each partition corresponds to one neuron, which is in general a higher-order neuron. The partition is performed by iterating the neuron weights in an attempt to maximize a defined criterion function. The method is implemented on several examples and is found to give good results. In the second implemented example the method obtained a good solution, whereas the traditional adaptive resonance method and self-organizing maps produced unsatisfactory results. The method is fast, as it takes typically from about 2 to 5 iterations to coverage. Although the proposed method is prone to get stuck in local minima, this did happen in the simulations in only very difficult problems and this problem could be solved by using gradient algorithms for searching for the global maximum, like the Tunneling Algorithm.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 31, 1991
Accession Number
ADA253187

Entities

People

  • Amir F. Atiya
  • Yaser S. Abu-mostafa

Organizations

  • California Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Computer Science
  • Computers
  • Frequency
  • Image Recognition
  • Iterations
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Probability
  • Probability Distributions
  • Random Variables
  • Recognition
  • Resonance
  • Simulations
  • Unsupervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Modeling and Simulation
  • Robotics and Automation.

Technology Areas

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