Towards Efficient, Interpretable, and Robust Deep Learning
Deep learning has been achieving very impressive improvement in many applications such as computer vision. In the literature, however, many theoretical and empirical questions still remain elusive. Why does deep learning work so well? How should we design a network for a specific task (in a principal way)? Can we train a network better and faster? Can we learn a network that can be deployed in embedded systems?
To answer such questions, in this talk I will provide some insight on three important issues in deep learning, i.e., efficiency, interpretability, and robustness, from the perspective of optimization. Specifically in my talk, efficiency aims to accelerate the computation of deep models as well as preserving their high accuracy. Interpretability aims to understand the physical meaning of the training objectives in deep learning (including the network architectures). Robustness aims to analyze the convergence and generalization of deep models. I will present some algorithms and results from my works on efficient training of deep models, learning to compress deep models, regularized deep networks, and convergence and generalization bound of stochastic momentum. Some of these works have been applied to real products in computer vision and geoscience, and I hope that my works can continue to contribute to other communities such as healthcare, security & privacy, robotics, and energy & sustainability.
Dr. Ziming Zhang
Research Scientist, Mitsubishi Electric Research Laboratories (MERL)
Dr. Ziming Zhang is currently a Research Scientist at Mitsubishi Electric Research Laboratories (MERL) since 2016. Before joining MERL he was a Research Assistant Professor at Boston University in 2015-2016. He completed his PhD from Oxford Brookes University, U.K., in 2013 under the supervision of Prof. Philip Torr (now a professor at University of Oxford). His research interest lies in computer vision and machine learning, including object recognition and detection, person re-identification, zero-shot learning, optimization, deep learning, etc. His works have appeared in TPAMI, CVPR, ICCV, ECCV and NIPS. He serves as a reviewer/PC member in the top-tier conferences such as CVPR, ICML, NIPS, AAAI, AISTats, IJCAI, and ICLR. He won R&D100 Award, 2018.
Host: Professor Donald Brown