Research Output per year
A conventional neural network approach to regression problems approximates the conditional mean of the output vector. For mappings which are multi-valued this approach breaks down, since the average of two solutions is not necessarily a valid solution. In this article mixture density networks, a principled method to model conditional probability density functions, are applied to retrieving Cartesian wind vector components from satellite scatterometer data. A hybrid mixture density network is implemented to incorporate prior knowledge of the predominantly bimodal function branches. An advantage of a fully probabilistic model is that more sophisticated and principled methods can be used to resolve ambiguities.
|Place of Publication||Birmingham|
|Number of pages||8|
|Publication status||Published - 22 Oct 1998|
- wind vector retrieval
- ERS-1 satellite
- probabilistic models
- mixture density networks
- neural networks
Structured neural network modelling of multi-valued functions for wind retrieval from scatterometer measurementsEvans, D. J., Cornford, D. & Nabney, I. T., Jan 2000, In : Neurocomputing. 30, 1-4, p. 23-30 8 p.
Research output: Contribution to journal › Article