Efstratios Gavves
[advanced] Advanced Deep Learning [virtual]
Summary
Deep Learning Dynamics. Deep Learning has changed the face of AI in the past decade. One of the most exciting future directions is in the interface of Deep Learning, Temporality, Dynamics and Dynamical Systems, which is especially interesting for applications in the Sciences and Engineering. In this short course we will visit Deep Learning from the lens of Dynamical Systems, ODEs, PDEs, and generally spatiotemporal data.
Syllabus
- Neural Networks as Dynamical Systems
- Neural Networks for Dynamical Systems
- Neural Networks for Video Learning, Causality, Tracking
- Neural Networks for Sciences
References
Pre-requisites
Basic understanding of neural networks, probability theory, linear algebra, calculus.
Short bio
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.
