【学术预告】Towards Robust ResNet: A Small Step but A Giant Leap-正规赌平台网址-全国十大赌博官网

正规赌平台网址

  • 科学研究Research

  • 研究机构
  • 学术动态
  • 人才培养Academic

  • 本科教育
  • 研究生教育
  • 研究生论坛
  • 实训就业
  • 海外经历
  • 学生工作Student

  • 本科
  • 研究生
  • 人才招聘Recruitment

  • 校友工作Alumni

  • 学院校友会管理办法
  • 杰出校友
  • 办公指南Guide

  • 规章制度
  • 院内信息Information

  • 学术动态

    当前位置: 首页 > 科学研究 > 学术动态 > 正文

    【学术预告】Towards Robust ResNet: A Small Step but A Giant Leap

    发布日期:2019-05-15    作者:     来源:     点击:

    时间:2018年5月23日(周四)下午2:30

    地点:正规赌平台网址数媒楼110会议室

    报告题目:Towards Robust ResNet: A Small Step but A Giant Leap

    报告摘要:We bring in a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a deep neural network can be interpreted using a partial differential equation, which naturally inspires us to characterize ResNet by an explicit Euler method. Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization. Specifically, we prove that a small step factor h can benefit the training robustness for back-propagation; from the view of forward-propagation, a small h can aid in the robustness of the model generalization. A comprehensive empirical evaluation on both vision CIFAR-10 and text AG-NEWS datasets confirms that a small h aids both the training and generalization robustness.

    报告人:Jingfeng Zhang is pursuing his Ph.D. degree under the supervision of Asst. Prof. Kian Hsiang Low & Prof. Mohan Kankanhalli at AI Singapore & N-CRiPT Center, at National University of Singapore. He currently works on robust machine learning collaborating with RIKEN-AIP and IBM Singapore. He is also a part-time consultant at ADDO AI. His current research interests lie in robustness in machine learning and privacy-preserving for machine learning.

    地址:中国济南高新技术产业开发区舜华路1500号        邮编:250101

    电话:(86)-531-88391516        传真:(86)-531-88391686

    扫一扫
    关注公众号