Loading Events

« All Events

  • This event has passed.

CESG Seminar: “Embracing Sparsity in Deep Networks: From Algorithms to Hardware”

October 13 @ 4:10 pm - 5:10 pm

| Free

Abstract: In this talk, I will present how the sparsity, a desirable property for both algorithms and hardware design, could be discovered, exploited, and enhanced in the context of deep networks. I will first introduce how an iterative sparse solver could be linked to and tuned as a feed-forward deep network, using the “unfolding then truncating” trick. Next, I will show how a double sparse dictionary structure could be naturally utilized to sparsify the weights of the obtained networks resulting in a new deep network whose feature and parameter spaces are simultaneously sparsified. I will then describe PredictiveNet, a recent work by one of my collaborators, which predicts the zero hidden activations of the nonlinear CNN layers at low costs thereby skipping a large fraction of convolutions in CNNs at runtime without modifying the CNN structure or requiring additional branch networks. Such an energy-efficient hardware implementation could be seamlessly integrated with the theory bridging sparse optimization and deep learning, potentially leading to even larger energy savings.

Bio: Dr. Zhangyang (Atlas) Wang is an Assistant Professor of Computer Science and Engineering (CSE), at the Texas A&M University (TAMU), since August 2017. He is currently leading a research group of 5 Ph.D. students and 3 M.S. students and has several projects supported by DARPA, Adobe, etc. During 2012-2016, he was a Ph.D. student in the Electrical and Computer Engineering (ECE) Department, at the University of Illinois at Urbana-Champaign (UIUC), working with Professor Thomas S. Huang. Prior to that, he obtained the B.E. degree at the University of Science and Technology of China (USTC) in 2012. Dr. Wang’s research has been addressing machine learning, computer vision and multimedia signal processing problems using advanced feature learning and optimization techniques. He has co-authored 40 papers, and published several books and chapters. He has been granted 3 patents, and has received over 15 research awards and scholarships. His research has been covered by worldwide media such as BBC, Fortune, International Business Times, UIUC news and alumni magazine. More can be found at: http://www.atlaswang.com.

Details

Date:
October 13, 2017
Time:
4:10 pm - 5:10 pm
Cost:
Free

Venue

WEB, Room 236-C
Wisenbaker Engineering Building
Website:
http://ecencesg.wpengine.com