JOSA TechTalks: State of the Art Machine Learning

Machine learning is a quickly evolving domain due to the fast progress of the techniques used and the huge computing power that's easily available for everyone to use.

In this talk, Sami Abu-El-Haija from Google Research will be giving an overview of modern machine learning algorithms and the state-of-the-art in various ML domains including computer vision, natural language understanding and graph-structured data.
Sami will touch on how someone can train a state-of-the-art machine learning model using modern technologies (specifically using TensorFlow).

Knowledge of matrix calculus, optimization theory, and programming is not required but is nice to have.

Speaker bio:
Sami Abu-El-Haija is a Machine Learning Researcher at Google Research in California. He specializes in deep learning for computer vision and graph-structured data. Concurrently, he is starting his Computer Science Ph.D. at the University of Southern California, focusing on information theory and its applications to machine learning. He holds a bachelors degree in Electrical Engineering from the University of Toronto, and a masters degree from the University of Michigan - Ann Arbor, in Computer Engineering.