学术报告报告题目：Reproducible and Efficient Automated Deep Learning
报 告 人：董宣毅 博士（悉尼科技大学）
报告时间：2020年11月25日（周三）下午15:00-16:00
报告地点：4号楼4318室
邀 请 人：刘深泉 教授
欢迎广大师生前往！
数学学院
2020年11月24日
报告摘要：
In the past years, automated deep learning (AutoDL) significantly reduced manual efforts and improved deep model design, hyper-parameter selection, etc. Despite these exciting improvements, the quality of scientific empirical evaluations in the young AutoDL is still lacking behind that of other DL areas. In this talk, I will introduce how to do reproducible research in AutoDL and my recent progress on efficient AutoDL.
报告人简介：
Xuanyi Dong is a Ph.D. student at the University of Technology Sydney. He has extensive industrial experience, such as about three years' internship at Google Brain and Facebook Reality Lab. During his Ph.D. study, he has published more than 20 papers on CVPR/ICLR/TPAMI/etc with citations 1500+. He was awarded the 2019 Google Ph.D. Fellowship. He was one of the winners at TRECVID Video Localization 2016 and ranked second at ILSVRC Object Localization 2015.