Cпецсеминар группы байесовских методов: The Machine Learning of Time and Dynamics … with an Outlook towards the Sciences

В эту пятницу, 29 октября, состоится очередной спецсеминар группы байесовских методов.

Начало в 16 00 (мск) Язык семинара: английский

Выступит: Dr. Efstratios Gavves, Associate Professor at the University of Amsterdam Dr. Efstratios Gavves is an Associate Professor at the University of Amsterdam in the Netherlands, an ELLIS Scholar, and co-founder of Ellogon.AI. He is a director of the QUVA Deep Vision Lab with Qualcomm, and the POP-AART Lab with the Netherlands Cancer Institute and Elekta. Efstratios received the ERC Career Starting Grant 2020 and NWO VIDI grant 2020 to research on the Computational Learning of Time for spatiotemporal sequences and video. His background is in computer vision, and the last several years moved his interest to temporal machine learning and systems dynamics, efficient computer vision, and machine learning for oncology.

Тема: The Machine Learning of Time and Dynamics … with an Outlook towards the Sciences

Абстракт: In the past decades, the impressive progress in machine learning and applications -like computer vision- was mainly by assuming (or enforcing) that data is static and usually of spatial-only nature, that data is i.i.d, that learning correlations suffices for high predictive accuracies. In the real world, however, data and processes are typically (spatio-) temporal, dynamic, non-stationary, non-iid, causal. This leads to paradoxical situations for learning algorithms. In this talk, I will first present my vision for a new type of learning that embraces temporality and dynamics. I will then discuss recent work that connects complexity in deep stochastic models, like hierarchical VAEs, with phase transitions, pointing perhaps to a link to statistical physics. I will continue with discussing how simple ways of introducing roto-translation equivariance can greatly improve standard neural relational inference in modelling dynamics of complex interacting dynamical systems. Last, I will present our latest attempts in scaling up causal discovery by at least two orders of magnitude compared to the recent literature. I will close with drawing a connection between machine learning and the sciences, whose interface -I believe- is deeply temporal and dynamical, and will inspire the great next breakthroughs.