当前位置: 学院首页 > 学术科研 > 学术看板 > 正文

学术报告——Bridging Deep Neural Networks and Differential Equations for Image Restoration and Beyond

日期:2018-09-12 来源: 作者: 浏览:

报告题目:Bridging Deep Neural Networks and Differential Equations for Image Restoration and Beyond






Deep learning continues to dominate machine learning. It is now widely used in many research areas in science and engineering, and has major industrial impacts. Deep learning methods have achieved remarkable results in a variety of tasks, especially in a supervised learning environment.

In this talk, I will start with a brief review of classical (pre deep learning) image restoration methods, followed by some recent applications of deep learning in image restoration and image analysis. These models inspired some of our recent work on combining numerical differential equation and deep convolutional architecture design. We can interpret some of the state-of-the-art 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 propose a new moving endpoint control model to denoise images with unknown noise levels. We also show how to design transparent deep feed-forward convolutional networks to accurately predict dynamics of complex systems and with a potential to uncover the underlying hidden PDE models.


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、20112014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50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,2015年入选中组部第十一批“千人计划”青年人才。





上一条:学术报告——Efficient numerical methods for L0-norm related minimizations