Defence of dissertation in the field of Computer Science, Sami Remes, M.Sc. (Tech.)
The dissertation "Modelling non-stationary functions with Gaussian processes" presents non-stationary kernel functions for Gaussian processes, which can be utilized in modelling changing dependencies between different measurements over time, for example. Moreover, these kernel functions can be learned from data, so that the modeller does not need to define a suitable kernel by hand.
Opponent: Dr. Seth Flaxman, Imperial College London, UK
Custos: Professor Samuel Kaski, Aalto University School of Science, Department of Computer Science
Contact information: Sami Remes, Department of Computer Science, +358 40 8655165, [email protected]