公共目录

您目前的位置: 首页» 公共目录» 学术活动

学术报告: Should We Go Deep and How Deep?

题目: Should We Go Deep and How Deep?

主讲人: Hairong Qi 教授,美国田纳西大学

时间: 2017年9月19日上午9:30

地点: 信息工程学院小会议室

主办单位: 首都师范大学信息工程学院

主讲人介绍:Hairong Qi received the B.S. and M.S. degrees in computer science from Northern JiaoTong University, Beijing, China in 1992 and 1995, respectively, and the Ph.D. degree in computer engineering from North Carolina State University, Raleigh, in 1999. She is currently the Gonzalez Family Professor with the Department of Electrical Engineering and Computer Science at the University of Tennessee, Knoxville. Her research interests are in advanced imaging and collaborative processing, hyperspectral image analysis, computer vision and machine learning. Dr. Qi is the recipient of the NSF CAREER Award. She also received the Best Paper Awards at the 18th International Conference on Pattern Recognition (ICPR’06), the 3rd ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC’09), and IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensor (WHISPERS’15). She is awarded the Highest Impact Paper from the IEEE Geoscience and Remote Sensing Society in 2012.

 

内 容 介 绍:In recent years, deep learning is gaining mainstream momentum in different disciplines of studies, especially in computer vision and natural language processing. This talk first reviews important timelines of deep learning development. It then gets into the discussion of engineered features vs. automatic features extracted by deep learning, which leads to the study of supervised deep learning, going from CNN to ResNet. The talk then moves onto the most recent development of generative adversarial networks (GANs) and elaborates on our development of conditional adversarial autoencoder for age progression/regression. The talk wraps up with a few thoughts on potential research directions of deep learning.