Teaching Computers to See and Think

The ability to see and think is essential for AI. In this talk I will give an overview of my group's recent work that aims to make computers see more and think better. First, I will present our efforts to advance image understanding from isolated objects to rich relational semantics and from 2D to 3D. Second, I will show how to use deep learning and vector embeddings to improve automated logical reasoning.
Jia Deng is an Assistant Professor of Computer Science and Engineering at the University of Michigan. His research focus is on computer vision and machine learning. He received his Ph.D. from Princeton University and his B.Eng. from Tsinghua University, both in computer science. He is a recipient of the PAMI Mark Everingham Prize, the Yahoo ACE Award, a Google Faculty Research Award, the ICCV Marr Prize, and the ECCV Best Paper Award.