一叶知秋:少数学习的最新进展报告题目
一叶知秋:Recent Advances in Few-Shot Learning
罗杰波   Jiebo Luo
报告人照片   Jiebo Luo is a Professor of Computer Science at the University of Rochester. Dr. Luo is a Fellow of SPIE, IAPR, IEEE, ACM, and AAAI.
  The small data challenges have emerged in many learning problems because the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address the challenges, many efforts have been made on training complex models with small data in an unsupervised and semi-supervised fashion. While many researchers focus on the unsupervised and semi-supervised methods, we will provide an overview of other recent advances, from unsupervised and semi-supervised domain adaptation to few-shot learning. While it is impossible to prepare an encyclopedia of all related works, we seek to cover this research frontier by revealing where we are on the journey towards overcoming the small data challenges.
报告时间:2019年08月06日15时30分    报告地点:西区科技西楼1213会议室
报名截止日期:2019年08月06日    可选人数:50