本讲教师：C.-C. Jay Kuo
报告人简介：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 IFS in 2012-2014. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. Dr. Kuo is a co-author of 280 journal papers, 920 conference papers and 14 books. Given a convolutional neural network (CNN) architecture, its network parameters are determined by backpropagation (BP) nowadays. The underlying mechanism remains to be a black-box after a large amount of theoretical investigation. In this talk, I describe a new interpretable feedforward (FF) design with the LeNet-5 as an example. The FF-designed CNN is a data-centric approach that derives network parameters based on training data statistics layer by layer in one pass. To build the convolutional layers, we develop a new signal transform, called the Saab (Subspace approximation with adjusted bias) transform. The bias in filter weights is chosen to annihilate nonlinearity of the activation function. To build the fully-connected (FC) layers, we adopt a label-guided linear least squared regression (LSR) method. To generalize the FF design idea furthermore, we present the notion of “successive subspace learning (SSL)” and present a couple of concrete methods for image and point cloud classification. Extensive experimental results are given to demonstrate the competitive performance of the SSL-based systems.