新闻中心

《Journal of Imaging Science and Technology》Editor-in-Chief, Dr. Chunghui Kuo学术报告11月16日 下午

发布时间:2023-11-13浏览次数:266

报告题目:DEEP LEARNING FOR IMAGE PROCESSING AND COMPUTER VISION: FROM A SIGNAL SENSING VIEWPOINT

时间:2023年11月16日 (星期四) 下午3:00

地点:计算机与网络空间安全学院大楼507

主办:计算机与网络空间安全学院, 数字福建环境监测物联网实验室

参加对象:计网学院感兴趣的老师和学生

报告摘要:

The fundamental question of machine learning is to find a rich class of functionals which can map from a high-dimensional space of raw data to a low-dimensional collections of actionable outcomes under the constraint of being computationally trackable. While deep learning has gained significant success in image processing, computer vision and natural language processing, the deep and complicated network construction and extensive reliance on numerical optimization has made theoretical analysis of these deep learning networks extremely challenging. The objective of this presentation is to go beyond optimization and attempt to re-evaluate our basic understanding of deep learning through the lens of signal sensing in high dimensional space. At last, an outlook of the AI industry will be presented to show projected future growth opportunities, scientific and technological challenges, and potential societal risks.

报告人简介:

Chunghui Kuo is the Editor-in-Chief at the Journal of Imaging Science and Technology and lecturer in the Mathematics Department at the State University of New York Geneseo.

He received his Ph.D. in Electrical and Computer Engineering from the University of Minnesota and joined Eastman Kodak Company in 2001. He was a senior image scientist, a Distinguished Inventor, and served as an Intellectual Property Coordinator at the Eastman Kodak Company. He holds 55 US patents and 10 Chinese patents, where his patented automatic white-blending workflow received 2017 Canadian Printing Award. He had served as an industrial standardization committee member from 2005 to 2008 at the International Organization for Standardization (ISO).

He is a senior member of the IEEE Signal Processing Society and his research interests are in image processing, computer vision, blind signal separation and classification, and artificial intelligence applied in signal/image processing.