Unveil Convolutional Neural Networks (CNNs) via Interpretable Initialization
|講者：||Prof. C.-C. Jay Kuo|
|時間：||2018-10-26 (Fri) 10:30 - 12:00|
The superior performance of Convolutional Neural Networks (CNNs) has been demonstrated in many applications such as image classification, detection and processing. Yet, CNN’s working principle remains a mystery. In this talk, I will shed light on the underlying operational principle of CNNs using an interpretable initialization. The roles of convolutional operations, the bias term, nonlinear activation, max pooling, convolutional layers and fully connected layers can be well explained through this initialization. The initialization offers a very good result without backpropagation, and the backpropagation can be used to finetune the initial result for higher accuracy. I will use a couple of networks to show the effectiveness of this new initialization method on both the MNIST and the CIFAR-10 datasets.
Dr. C.-C. Jay Kuo received his Ph.D. degree from the Massachusetts Institute of Technology in 1987. He is now with the University of Southern California (USC) as Director of the Media Communications Laboratory and Distinguished Professor of Electrical Engineering and Computer Science. His research interests are in the areas of media processing, compression and understanding. Dr. Kuo was the Editor-in-Chief for the IEEE Trans. on Information Forensics and Security in 2012-2014. He was the Editor-in-Chief for the Journal of Visual Communication and Image Representation in 1997-2011, andserved as Editor for 10 other international journals. Dr. Kuo received the 1992 National Science Foundation Young Investigator (NYI) Award, the 1993 National Science Foundation Presidential Faculty Fellow (PFF) Award, the 2010 Electronic Imaging Scientist of the Year Award, the 2010-11 Fulbright-Nokia Distinguished Chair in Information and Communications Technologies, the 2011 Pan Wen-Yuan Outstanding Research Award, the 2014 USC Northrop Grumman Excellence in Teaching Award, the 2016 USC Associates Award for Excellence in Teaching, the 2016 IEEE Computer Society Taylor L. Booth Education Award, the 2016 IEEE Circuits and Systems Society John Choma Education Award, the 2016 IS&T Raymond C. Bowman Award, and the 2017 IEEE Leon K. Kirchmayer Graduate Teaching Award. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. He has guided 145 students to their Ph.D. degrees and supervised 27 postdoctoral research fellows. Dr. Kuo is a co-author of 260 journal papers, 900 conference papers and 14 books.