GAMES Webinar 2019 – 92期(深度学习可解释性专题课程) | 孙剑（西安交通大学），苏航（清华大学）

【GAMES Webinar 2019-92期】
报告嘉宾：孙剑，西安交通大学

报告时间：2019年4月25日 晚8:00-8:45（北京时间）
主持人：樊鑫，大连理工大学（个人主页：http://faculty.dlut.edu.cn/Xin_Fan/zh_CN/xsry/1014819/list/index.htm）
报告题目：可解释深度学习探索：模型驱动深度学习

报告摘要：

经典的深度学习方法将标准深度神经网络作为黑箱进行数据驱动的目标任务学习。我们提出模型驱动的深度学习思想，

将传统的基于领域知识或物理机制的建模方法与深度神经网络的数据驱动学习能力相结合，构建模型驱动的深度学习方法。在该报告中，将展示我们在模型驱动深度学习方法上的一些研究成果，包括统计模型驱动的深度学习方法、ADMM优化算法驱动的压缩传感深度神经网络、元学习优化算法等。并展示它们在图像处理与分析、深度神经网络优化中应用中的有效性。

讲者简介：

西安交通大学教授，博士生导师。2009年获得西安交通大学应用数学博士学位。基金委“优青”项目、万人计划“青年拔尖人才支持计划”项目入选者。主要关注影像分析与处理的数学方法、人工智能的基础算法研究，相关成果发表于IEEE PAMI, IJCV, MIA, IEEE TIP, CVPR, NIPS,MICCAI等领域内高水平国际期刊和会议。曾经在微软亚洲研究院（2005-2008）、美国中佛罗里达大学（2009-2010）、法国巴黎高等师范学院与法国国家信息与自动化研究院（2012-2014）做博士后或访问学者。获得中国工业与应用数学学会优秀青年学者奖。

讲者个人主页：http://gr.xjtu.edu.cn/web/jiansun

报告嘉宾：苏航，清华大学

报告时间：2019年4月25日 晚8:45-9:30（北京时间）
主持人：樊鑫，大连理工大学（个人主页：http://faculty.dlut.edu.cn/Xin_Fan/zh_CN/xsry/1014819/list/index.htm）
报告题目：  Towards Interpretable and Robust Artificial Intelligence

报告摘要：

Artificial intelligence techniques such as deep neural networks have become an indispensable tool on an increasing number of complex tasks, but these models are usually applied in a black box manner. In this talk, we intend to carry out a systematic investigation of how to build an interpretable artificial intelligence framework by bridging the gap between the abstract latent features and human concepts. We further apply the new interpretable machine learning framework to learn robust representations such that adversarial samples can be detected and recognized effectively.

讲者简介：

Dr. Hang Su is an assistant professor in the Department of Computer Science and Technology at Tsinghua University. Before joining Tsinghua, he received his Ph. D. degree from Shanghai Jiaotong University in 2014 and worked as a visiting scholar at Carnegie Mellon University from 2011 to 2013. His research interests lie in the development of computer vision and machine learning algorithms for solving scientific and engineering problems arising from artificial learning and reasoning. His current work involves both the foundations of interpretable machine learning and the applications of image/video analysis, based on which he has published around 50 papers including CVPR, ECCV, TMI, etc. He has served as senior PC or PC members in the dominant international conferences including IJCAI, AAAI, CVPR, and worked as reviewers for top journals such as TPAMI, TIP, TMI, etc. He received “Young Investigator Award” from MICCAI2012, the “Best Paper Award” in AVSS2012, and “Platinum Best Paper Award” in ICME2018, “Annual Outstanding Paper Award” in valsie2019.

讲者个人主页：http://www.suhangss.me/

GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接：http://webinar.games-cn.org