Visual Perception for Better Understanding of Sports Games
his talk will be about some of the main challenges in developing and deploying deep learning algorithms at scale, i.e. processing more than 60,000 sports videos which are coming from different sources, and touches the issues from proper problem definition to generalization and robustness in the deep learning models.
Bahar Pourbabaee holds a PhD degree in Electrical and Computer Engineering with over a decade of experience in machine learning and estimation theory and also a diverse background from designing safety critical systems for aircraft control to the bimedial signal processing for healthcare application. She came to the sport technology world to build machines that understand and predict sport games. At Sportlogiq, she is the machine learning team lead for the Montreal office and contributing to the development of intelligent machines using state-of-the-art deep learning and time series analysis techniques with a focus on analyzing and understanding spatio-temporal data.