會議號：170 678 3077
The superior performance of neural networks has been demonstrated in many applications such as image classification, detection and processing. Yet, their working principle remains a mystery. In this talk, I will present work on interpretable neural networks developed in the last 4-5 years. The first topic is about interpretable multilayer perceptron (MLP). A connection is built between the classical two-class linear discriminant analysis (LDA) and the MLP. Based on this connection, we can obtain an interpretable MLP design that specifies the network architecture and all filter weights in a feedforward one-pass fashion. The second topic is about interpretable convolutional neural networks (CNNs). The convolutional layers of CCNs can be viewed as a sequence of spatial-spectral signal transforms while the fully connected layers of CNNs can be interpreted as multi-stage linear least-squared regressors. Through such interpretations, one can also design CCNs in a feedforward one-pass manner. Application examples based on interpretable designs will be given.
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 visual computing and communication. He is a Fellow of AAAS, IEEE and SPIE. Dr. Kuo’s research interests are in the areas of multimedia computing and data science and engineering. He has received numerous awards for his outstanding research contributions, including 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 2019 IEEE Computer Society Edward J. McCluskey Technical Achievement Award, the 2019 IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award and the 2020 IEEE TCMC Impact Award. Dr. Kuo has guided 155 students to their PhD degrees and supervised 30 postdoctoral research fellows. His educational achievements have won a wide array of recognitions such as 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, the 2017 IEEE Leon K. Kirchmayer Graduate Teaching Award, the 2017 IEEE Signal Processing Society Carl Friedrich Gauss Education Award, and the 2018 USC Provost’s Mentoring Award