Mathematical and Numerical Analysis Aspects of Quasi-Neural Networks

Abstract

Basic results were obtained and published on the mathematical characterization of feed-forward and recurrent neural networks. It was shown how to approximate any continuous function by a 3-layer feed-forward network. The fixed-points and oscillations of recurrent networks were analyzed. Neural networks, dynamical systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 27, 1992
Accession Number
ADA248583

Entities

People

  • Edward K. Blum

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Classification
  • Computer Programs
  • Computers
  • Content Addressable Memory
  • Difference Equations
  • Differential Equations
  • Dynamics
  • Equations
  • Mathematics
  • Neural Networks
  • Numerical Analysis
  • Oscillation
  • Oscillators
  • Recurrent Neural Networks

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks