Contact
Phillip Isola Associate Professor, Department of Electrical Engineering and Computer Science
Generative models can now produce realistic and diverse synthetic data in many domains. This makes them a viable choice as a data source for training downstream AI systems. Unlike real data, synthetic data can be steered and optimized via interventions in the generative process. I will share my view on how this makes synthetic data act like data++, data with additional capabilities. I will discuss the advantages and disadvantages of this setting, and show several applications toward problems in computer vision and robotics.
James Kirtley Professor, Electrical Engineering
Devavrat Shah Professor of Electrical Engineering
Moderator: Steve Whittaker Program Director, MIT Industrial Liaison Program
Panelists: Sanjay Bajekal Senior Technical Fellow, Research, Collins Aerospace
Shahriar Khushrushahi Founder and CEO, Notch
David Clark Senior Research Scientist, MIT Computer Science and Artificial Intelligence Laboratory