题目: Bridging Deep Neural Networks and Differential Equations for Image Analysis and Beyond  
  
  

报告人：董彬  研究员（北京大学）

报告时间：2019.11.11下午2:00-3:00  

报告地点：数学学院E404（沙河校区）

摘要:      Deep learning continues to dominate machine learning and has been successful in computer vision, natural language processing, etc. Its impact has now expanded to many research areas in science and engineering. However, the model design of deep learning still lacks systematic guidance, and most deep models are seriously in lack of transparency and interpretability, thus limiting the application of deep learning in some fields of science and medicine. In this talk, I will show how we can tackle this issue by presenting some of our recent work on bridging numerical differential equation and deep convolutional architecture design. We can interpret some of the popular deep CNNs in terms of numerical (stochastic) differential equations, and propose new deep architectures that can further improve the prediction accuracy of the existing networks in image classification. We also show how to design transparent deep convolutional networks to uncover hidden PDE models from observed dynamical data. Further applications of this perspective to various problems in imaging and inverse problems will be discussed.  
  

报告人简介：董彬，北京大学，北京国际数学研究中心研究员、北京大数据研究院深度学习实验室研究员、生物医学影像分析实验室副主任。2009年在美国加州大学洛杉矶分校（UCLA）数学系获得博士学位。博士毕业后曾在美国加州大学圣迭戈分校（UCSD）数学系任访问助理教授、2011－2014年在美国亚利桑那大学（University of Arizona）数学系任（Tenure-Track）助理教授，2014年底入职北京大学。主要研究领域为应用调和分析、优化方法、机器学习、深度学习及其在图像和数据科学中的应用。应用包括图像重建及修复、生物与医学成像、生物医学影像分析、疾病量化、治疗方案优化等问题，在包括《Journal of the American Mathematical Society》、《Applied and Computational Harmonic Analysis》、《SIAM系列期刊》、《Inverse Problems》、《Mathematics of Computation》、《Journal of the Royal Statistical Society Series B》、《MICCAI》、《ICML》在内的国际重要学术期刊和会议上发表论文60余篇，拥有2项美国专利，现任期刊《Inverse Problems and Imaging》副主编。于2014年获得香港求是基金会的“求是杰出青年学者奖”。

邀请人：刘铁钢