Regularised mixture density networks for modelling wind direction

Lars U. Hjorth, Ian T. Nabney

Research output: 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

Fingerprint

wind direction
satellite data
weather
modeling
experiment
parameter
technical information

Keywords

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

Cite this

Hjorth, L. U., & Nabney, I. T. (1999). Regularised mixture density networks for modelling wind direction. Birmingham: Neural Computation Research Group.
Hjorth, Lars U. ; Nabney, Ian T. / Regularised mixture density networks for modelling wind direction. Birmingham : Neural Computation Research Group, 1999.
@techreport{8e50b91873a34f7e821dcc72a35778e0,
title = "Regularised mixture density networks for modelling wind direction",
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'.",
keywords = "Mixture Density Networks, RBF network, fixed kernel, wind direction, satellite data, e ersII weather satellite",
author = "Hjorth, {Lars U.} and Nabney, {Ian T.}",
year = "1999",
language = "English",
publisher = "Neural Computation Research Group",
type = "WorkingPaper",
institution = "Neural Computation Research Group",

}

Hjorth, LU & Nabney, IT 1999 'Regularised mixture density networks for modelling wind direction' Neural Computation Research Group, Birmingham.

Regularised mixture density networks for modelling wind direction. / Hjorth, Lars U.; Nabney, Ian T.

Birmingham : Neural Computation Research Group, 1999.

Research output: Working paperTechnical report

TY - UNPB

T1 - Regularised mixture density networks for modelling wind direction

AU - Hjorth, Lars U.

AU - Nabney, Ian T.

PY - 1999

Y1 - 1999

N2 - 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'.

AB - 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'.

KW - Mixture Density Networks

KW - RBF network

KW - fixed kernel

KW - wind direction

KW - satellite data

KW - e ersII weather satellite

M3 - Technical report

BT - Regularised mixture density networks for modelling wind direction

PB - Neural Computation Research Group

CY - Birmingham

ER -

Hjorth LU, Nabney IT. Regularised mixture density networks for modelling wind direction. Birmingham: Neural Computation Research Group. 1999.