报告题目：Machine Learning: From Shallow Architecture to Deep Architecture
For the past few years, we have witnessed a great success of deep learning with deep neural network architecture. In this talk, I shall first briefly review the history of machine learning with Artificial Neural Networks (ANNs) and the major milestones of ANN theory and applications. I shall then discuss the architectures, training algorithms, and merits and drawbacks of deep learning with deep neural network architecture. Applications of deep learning in object detection and recognition, facial expression recognition, games (AlphaGo etc.), and Natural Language Processing (NLP) will be explored. I will end the talk with some reasonable predictions of deep learning and its impact on our daily life in the future.
Zheru Chi received his BEng and MEng degrees from Zhejiang University in 1982 and 1985, respectively, and PhD degree from the University of Sydney in March 1994. Between 1985 and 1989, he was on the Faculty of the Department of Scientific Instruments at Zhejiang University. He worked as a Senior Research Assistant/Research Fellow in the Laboratory for Imaging Science and Engineering at the University of Sydney from April 1993 to January 1995. In February 1995, he joined the Hong Kong Polytechnic University, where he is now an Associate Professor in the Department of Electronic and Information Engineering. Since 1997, he has served as Co-organizer of a Special Session/Session Chair/Area Moderator/Program Committee Member for a number of international conferences. He was a Contributor to Comprehensive Dictionary of Electrical Engineering (CRC Press and IEEE Press, 1999). He was an associate editor for IEEE Transactions on Fuzzy Systems between 2008 and 2010 and currently a technical editor for International Journal of Information Acquisition. Dr Chi started his research in artificial neural networks in the later 1980s and has witnessed this great wave of neural network resurgence since 1980s. He is one of the pioneers in combining neural networks and fuzzy systems for image processing and pattern recognition. Dr Chi and his research group have explored a wide range of applications of neural networks, including ECG classification, OCR, object recognition, image processing, image retrieval, facial expression, and natural language processing. His current research interests include pattern recognition, image processing, eye tracking data analysis, machine learning, and computational intelligence techniques. Dr. Chi has co-authored one book and 11 book chapters, and published more than 190 technical papers.