News & Events
Regularized Deep Learning with Geometry and Structures
Release time:May 15, 2018

Topic: Regularized Deep Learning with Geometry and Structures

Speaker: Dr. Qiang Qiu, Assistant Professor (Electrical and Computer Engineering Department, Duke University)

Date: May 17, 14:00-16:00

Venue: The 1st Conference Room, New Main Building


The central problem of deep learning is how to generalize well from training data to unseen data. One such solution is to regularize deep learning with priors encoded into models. In this talk, the speaker will discuss various techniques recently developed in regularizing deep learning with geometry, such as low-rank subspace and low-dimensional manifold, or structures over convolutional filters, nodes, and networks. The speaker will present numerous applications in cross-spectral face recognition, image hashing, object recognition, object localization, person re-identification, and privacy preservation.

Bio of the Speaker:

Dr. Qiu received his Bachelor's degree with first class honors in Computer Science in 2001, and his Master's degree in Computer Science from National University of Singapore in 2002. He received his Ph.D. degree in Computer Science from University of Maryland, College Park in 2013. During 2002-2007, he was a Senior Research Engineer at Institute for Infocomm Research, Singapore. He is currently with the Department of Electrical and Computer Engineering, Duke University. His research interests include machine learning, computer vision, and pattern recognition with applications in biometrics and imaging.



School of Electronic and Information Engineering