AI3 Seminar on Understanding Modern Machine-Learning November 10

The AI Innovation Institute (AI3) will present a seminar with Tel-Aviv University Professor Meir Feder titled, "Information-Theoretic Framework for Understanding Modern Machine-Learning," on Monday, November 10.

Information Theory views learning as universal prediction under log loss, characterized through regret bounds. Unlike the classical results that considered "small'" model classes and provided uniform regret, the proposed framework provides non-uniform, model dependent bounds utilizing an effective notion of architecture-based model complexity.

Feder is a professor and the Jokel Chair in Information Theory in the School of Electrical and Computer Engineering at Tel-Aviv University. He has received several academic and professional awards including the IEEE Information Theory Society best paper award and the Padovani lectureship. Parallel to his academic career, he founded five companies, among them Peach Networks and Amimon. Recently, with his renewed interest in machine learning and AI, he co-founded Run:ai, a virtualization, orchestration, and acceleration platform for AI infrastructure, acquired by Nvidia to support its GPU cloud operation.

For the technology he developed in Amimon, he received the 2020 Scientific and Engineering Award of the Academy of Motion Picture Arts and Sciences and was announced the principal inventor of the technology that attained the 73rd Engineering Emmy Award of the Television Academy.

The seminar will begin at 12;30 pm in the New Computer Science Building, Room 120.