Neural networks at work

  • Authors:
  • Dan Hammerstrom

  • Affiliations:
  • -

  • Venue:
  • IEEE Spectrum
  • Year:
  • 1993

Quantified Score

Hi-index 0.10

Visualization

Abstract

The benefits of neural networks and the types of application for which they are suited are outlined. Four representative applications are described in enough detail to show how they work. They are character recognition, function estimation, financial forecasting, and process control. Factors that have slowed the acceptance of neural networks are discussed. Hardware is briefly considered