报 告 人: 尚 奕 教授（美国密苏里大学）
报告时间: 2014年6月 25日（周三）9:30～11:00
报告地点: 校本部东区计算机大楼901室
邀 请 人: 刘福岩 副教授
Abstract：
In recent years, deep learning has been shown to achieve outstanding performance in a number of challenging real-world applications. The key idea of greedy layer-wise unsupervised pre-training followed by supervised fine-tuning is effective in overcoming the difficulty of local minima when training all layers of a deep neural network at once. In this work, a new active labeling framework for cost-effective selection of labeled data in deep learning is proposed and applied to a real-world application – emotion prediction via physiological sensor data, based on real-world, complex, noisy, and heterogeneous sensor data. On the MINIST dataset, the methods outperform random labeling consistently by a significant margin. For the application of deep learning to emotion prediction via physiological sensor data, a software pipeline has been developed. The system first extracts features from the raw data of four channels in an unsupervised fashion and then builds three classifiers to classify the levels of arousal, valence, and liking based on the learned features. The classification accuracy is 0.609, 0.512, and 0.684, respectively, which is comparable with existing methods based on expert designed features.
Biography：
Yi Shang is a Professor and the Director of Graduate Studies in the Computer Science Department, University of Missouri, Columbia, Missouri, USA. He received his Ph.D. degree in computer science from University of Illinois at Urbana-Champaign in 1997, M.S. degree from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, in 1991, and B.S. degree from the University of Science and Technology of China, Hefei, in 1988. He has published over 160 refereed papers in the areas of nonlinear optimization, wireless sensor networks, mobile computing, intelligent systems, and bioinformatics, and received 6 US patents. His research has been supported by NSF, NIH, Army, DARPA, Microsoft, and Raytheon. He is a lifetime member of ACM and senior member of IEEE.