Learning complex patterns with Gaussian processes (New FWO project)

Promotors: prof. Tom Dhaene, Dr. Ivo Couckuyt

Tom Dhaene (IDLab) - Deep learning models are a common tool to identify complex patterns in data. However, they still requires tens of thousands of training samples. In this project we investigate the use of Bayesian models such as the (deep) Gaussian process for deep learning and generative modeling modeling when data is scarce.