Sport Analytics and Hardware-Aware AI Algorithm

Sports Analytics - when Figures are more than Numbers by Christophe Ley

In this talk I will provide a gentle introduction to the growing world of sport analytics. After talking about its genesis and giving some striking examples from professional sports, I will describe some of the research carried out in my team MIDAS at the University of Luxembourg (partially in collaboration with professional sports teams), in particular how we can use statistics and machine learning to predict the outcome of sport events and inform coaches about the main determining factors behind these predictions, allowing to enhance their tactics.
I will conclude with an outlook on how these findings can be translated to sports medicine and, in particular, the estimation of injury risks.

Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity by Nilotpal Sinha
In this talk, I will present the problem of designing the neural network architecture tailored for edge devices (i.e. low powered devices). This is achieved by designing algorithms that automatically find the optimal architecture for a given computer vision task on a target edge device. More specifically, I will be presenting how this problem can be solved using multi-objective optimization algorithm which leads to lower computational resource utilization.