Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control

doi:10.1109/CCIS.2018.8691394

CORC > 新疆天文台 > 研究单元未命名 > 射电天文研究室 > 星系宇宙学研究团组

	Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control
	Xu, Wendi 1,2; Zhang, Ming 2,3
	2019-04-15
会议日期	November 23, 2018 - November 25, 2018
会议地点	Nanjing, China
关键词	Deep learning Cloud computing Computation theory Optical resolving power
DOI	10.1109/CCIS.2018.8691394
页码	470-474
国家	China
英文摘要	Despite its remarkable empirical success as a highly competitive branch of artificial intelligence, deep learning is often blamed for its widely known low interpretation and lack of firm and rigorous mathematical foundation. However, most theoretical endeavor is devoted in discriminative deep learning case, whose complementary part is generative deep learning. To the best of our knowledge, we firstly highlight landscape of empirical error in generative case to complete the full picture through exquisite design of image super resolution under norm based capacity control. Our theoretical advance in interpretation of the training dynamic is achieved from both mathematical and biological sides. 2018 IEEE.
产权排序	1
会议录	5th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2018
会议录出版者	Institute of Electrical and Electronics Engineers Inc.
语种	英语
URL标识	查看原文
ISBN号	9781538660041
内容类型	会议论文
源URL	[http://ir.xao.ac.cn/handle/45760611-7/3918]
专题	星系宇宙学研究团组
作者单位	1.University of Chinese Academy of Sciences, Beijing, 100876, China 2.Xinjiang Astronomical Observatories, Chinese Academy of Sciences, Urumqi, 830011, China 3.Key Laboratory for Radio Astronomy, Chinese Academy of Sciences, Nanjing, 210008, China;
推荐引用方式 GB/T 7714	Xu, Wendi,Zhang, Ming. Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control[C]. 见:. Nanjing, China. November 23, 2018 - November 25, 2018.