We present a general Bayesian framework for hyperparameter tuning in L2-regularized supervised learning models. Paradoxically, our algorithm works by first analytically integratin...
Recent decision-theoric planning algorithms are able to find optimal solutions in large problems, using Factored Markov Decision Processes (fmdps). However, these algorithms need ...
Thomas Degris, Olivier Sigaud, Pierre-Henri Wuille...
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
Independent Component Analysis is becoming a popular exploratory method for analysing complex data such as that from FMRI experiments. The application of such `model-free' me...
Nonlinear registration of 3D surfaces is important in many medical imaging applications, including the mapping of longitudinal changes in anatomy, or of multi-subject functional M...