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'.
|Publisher||Neural Computation Research Group|
|Publication status||Published - 1999|
- Mixture Density Networks, RBF network, fixed kernel, wind direction, satellite data, e ersII weather satellite