Rapid Training of GIL Neural Networks

Abstract

Applying generalized inverse learning to a feedforward neural network has been shown to be a effective tool in pattern recognition. The difficult computational step is finding the pseudo-inverse of a matrix. This paper develops an efficient method using differential equations to calculate the pseudo-inverse.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 28, 1999
Accession Number
ADA388753

Entities

People

  • Clark Jefferies
  • Louis Ntasin
  • Peter Kiessler

Organizations

  • Clemson University

Tags

Communities of Interest

  • Advanced Electronics
  • Air Platforms
  • Human Systems

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Computational Complexity
  • Convergence
  • Decomposition
  • Difference Equations
  • Differential Equations
  • Equations
  • Errors
  • Floating Point Operations
  • Guarantees
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Training
  • Transfer Functions

Readers

  • Artificial Intelligence
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Robotics and Automation.

Technology Areas

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