Recognising Simple Behaviours Using Time-Delay RBF Networks

  • Authors:
  • A. Jonathan Howell;Hilary Buxton

  • Affiliations:
  • School of Cognitive and Computing Sciences, University of Sussex, Falmer, Brighton BN1 9QH, UK. E-mail: jonh@cogs.susx.ac.uk, hilary@cogs.susx.ac.uk;School of Cognitive and Computing Sciences, University of Sussex, Falmer, Brighton BN1 9QH, UK. E-mail: jonh@cogs.susx.ac.uk, hilary@cogs.susx.ac.uk

  • Venue:
  • Neural Processing Letters
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents experiments using a radial basis function variant of thetime-delay neural network with image sequences of human faces. The network isshown to be able to learn simple behaviours based on y-axis head rotationand generalise on different data. The network model‘s suitability forfuture dynamic vision applications is discussed.