Datum / čas
Date(s) - 13.03.
11:00 - 13:00
CIIRC ČVUT B670
It is our pleasure to invite you to the following seminar organized by the IMPACT project:
Differentiation of Blackbox Combinatorial Solvers – Michal Rolinek (Max Planck Institute for Intelligent Systems, Germany)
Friday 2020-03-13 at 11:00
CIIRC Room B-670 (building B, floor 6)
Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial building blocks into neural networks. Such end-to-end architectures have the potential to tackle combinatorial problems on raw input data such as ensuring global consistency in multi-object tracking or route planning on maps in robotics. We present a method that implements an efficient backward pass through blackbox implementations of combinatorial solvers with linear objective functions. We provide both theoretical and experimental backing. In the talk, we will cover the description of the method including initial synthetic experiments (ICLR 2020), as well as two follow-ups; one on rank-based loss functions (may appear at CVPR 2020) and another regarding deep graph matching for keypoint correspondence.
More info: http://impact.ciirc.cvut.cz/seminars/#seminar2020-03-13-rolinek
For more information on IMPACT seminars, please visit http://impact.ciirc.cvut.cz/seminars