Title: Reproducible and Efficient Automated Deep Learning
Speaker: Dr. Xuanyi Dong ( University of Technology, Sydney )
Time: Wed, Nov.25 2020, PM: 15:00-16:00
Location: 4318, Building No.4, Wushan Campus
Inviter: Prof. Shenquan Liu
Abstract:
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.