2019.04.15 Bridging Deep Neural Networks and Differential Equations for Image Analysis and Beyond

2019-07-07 01:01:51 15



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

报告人:Dr. Bin Dong

Associate professor (tenured), Beijing International Center for Mathematical Research, Peking University


    点:北京大学吕志和楼B101报告厅(Rm. B101, Lui Che Woo Building)

主持人:张磊 研究员


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 famous 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 further expand this perspective to introduce a new moving endpoint control model to denoise images with unknown noise levels. We also show how to design transparent deep convolutional networks to uncover hidden PDE models from observed dynamical data and to predict the dynamical behavior accurately.



董彬,北京大学,北京国际数学研究中心长聘副教授、主任助理,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数学系任访问助理教授、20112014年在美国亚利桑那大学数学系任助理教授,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。在理论上,将图像领域独立发展近30年的两个数学分支(PDE/变分方法和小波方法)建立深刻的联系,改变了领域内对这两类方法的认识,拓宽了这两类方法的应用范畴。应用上,以数学理论为指导思想,为来源于医学影像、计算机视觉、深度学习等领域中的重要问题提供行之有效的解决方案。董彬在包括《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50余篇,拥有2项美国专利,现任期刊《Inverse Problems and Imaging》编委。2014年获得香港求是基金会的求是杰出青年学者奖,2015年入选中组部第十一批千人计划青年人才。