7月2日 董彬:Bridging Deep Neural Networks and Differential Equations for Image Analysis and Beyond

来源:中国足球竞彩比分 时间:2019-06-24浏览:116设置


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

主讲人:

主持人:沈超敏

开始来源:中国足球竞彩比分 时间:2019-07-02 08:30:00  结束来源:中国足球竞彩比分 时间:2019-07-02 09:30:00

讲座地址:中北校区理科大楼B1002

主办单位:计算机科学与软件工程学院

  

报告人简介:

       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。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》、《ICML》在内的国际重要学术期刊和会议上发表论文50余篇,现任期刊《Inverse   Problems and Imaging》编委。于2014年获得香港求是基金会的求是杰出青年学者奖。


报告内容:

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 and to predict the dynamical behavior accurately. Further applications of this perspective to various problems in imaging and inverse problems will be discussed.

  


返回原图
/