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.
Bibliographical noteSee http://eprints.aston.ac.uk/1412/
- 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., 22 Oct 1998, Birmingham: Aston University, 8 p.
Research output: Working paper › Technical report
Evans, D. J., Cornford, D., & Nabney, I. T. (2000). Structured neural network modelling of multi-valued functions for wind retrieval from scatterometer measurements. Neurocomputing, 30(1-4), 23-30. https://doi.org/10.1016/S0925-2312(99)00138-1