Organised by Neil Lawrence, Marc Dymetman.
For the launch talk detailing the theme for this programme see here.
Traditionally machine learning has focused mainly on constructing models in a data driven manner. Clearly, in practise, if we can incorporate domain knowledge with our learning we should be able to obtain improved performance. This type of knowledge is particularly important in application domains where data availability is sparse in the context of the complexity of the required model. In this thematic programme we will highlight and drive forward approaches to incorporating prior knowledge in the application domain. We are interested in all approaches to incorporating this prior knowledge and any application area. Already some subthemes (and application areas) are emerging within the programme for example: knowledge encoded in graph structures (applications in language and computational biology), knowledge encoded in ordinary and stochastic differential equations (applications in climate and systems biology) and knowledge encoded as probabilities (applications in language).
The Thematic Programme ran between March and September 2008.
The GREAT08 challenge, organised by Sarah Bridle, is about estimating the level of gravitational lensing in images of galaxies. This challenging task requires prior knowledge about the effect of gravitational lensing (which in turn informs us about how much Dark Matter there is) and the effect of a telescope's optics.