University of Cambridge > > Machine Learning @ CUED > Deep Gaussian processes and variational propagation of uncertainty

Deep Gaussian processes and variational propagation of uncertainty

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact dsu21.

The complex and potentially high-dimensional nature of real world data renders them difficult to visualise, understand and predict. This talk will discuss a family of Bayesian approaches for solving the aforementioned problems by combining the flexibility of Gaussian processes with the expressiveness of graphical and latent variable models. The general framework is referred to as a deep Gaussian process, from which interesting special cases emerge, for example time-series and multi-view models. The framework is accompanied by algorithmic pipelines which automate the process of learning rich representations from the data. To achieve principled regularisation it is essential to communicate the uncertainty across the different stages of the pipelines and the different components of the graphical models. Therefore, the talk will also present a set of mathematical developments which achieve this through variational inference. The above concepts and algorithms will be demonstrated with examples from computer vision (high-dimensional video, images), robotics (motion capture data, humanoid robotics) and dynamical systems.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity