Regularised mixture density networks for modelling wind direction

Lars U. Hjorth, Ian T. Nabney

Research output: Preprint or Working paperTechnical report

Abstract

This technical report contains all technical information and results from experiments where Mixture Density Networks (MDN) using an RBF network and fixed kernel means and variances were used to infer the wind direction from satellite data from the ersII weather satellite. The regularisation is based on the evidence framework and three different approximations were used to estimate the regularisation parameter. The results were compared with the results by `early stopping'.
Original languageEnglish
Place of PublicationBirmingham
PublisherNeural Computation Research Group
Publication statusPublished - 1999

Keywords

  • Mixture Density Networks
  • RBF network
  • fixed kernel
  • wind direction
  • satellite data
  • e ersII weather satellite

Fingerprint

Dive into the research topics of 'Regularised mixture density networks for modelling wind direction'. Together they form a unique fingerprint.

Cite this