Abstract:
Gaussian Process (GP) models are a versatile and useful tool in numerous problems in machine learning. This tutorial will start from a basic introduction to how GPs offer a principled, probabilistic and practical approach to non-linear modelling tasks. I’ll highlight how other frequently used methods are special cases of GPs, discuss more advanced topics such as approximate sparse methods, and show some successful applications.
Bio:
Carl Edward Rasmussen is a Reader in the Information Engineering Machine Learning Group in the Department of Engineering, University of Cambridge. He has a very broad interest in probabilistic inference in machine learning, covering both unsupervised, supervised and reinforcement learning. He is particularly interested in design and evaluation of non-parametric methods such as Gaussian processes and Dirichlet processes.