ÌâÄ¿£ºRegularized Deep Learning with Geometry and Structures

Ö÷½²£º³ðÇ¿ ½ÌÊÚ

ʱ¼ä£º5ÔÂ24ÈÕ£¨ÖÜËÄ£©15£º30

µØµã£ºÐÐÕþ±±Â¥Ò»Â¥Ñ§Êõ±¨¸æÌü

Ö÷°ì£ºÍ¨ÐŹ¤³ÌѧԺ

³ðÇ¿½ÌÊÚ¼ò½é£ºQiang Qiu received his Bachelor's degree with first class honors in Computer Science in 2001, and his Master's degree in Computer Science in 2002, from National University of Singapore. He received his Ph.D. degree in Computer Science in 2013 from  University of Maryland, College Park. 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.

±¨¸æÖ÷ÒªÄÚÈÝ£ºThe 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 we will discuss various techniques we recently developed in regularizing deep learning with geometry, such as low-rank subspace and low-dimensional manifold, or structures over convolutional filters. We will present numerous applications in cross-spectral face recognition, image hashing, image clustering, object recognition, object localization, and person re-identification.