报告主题： Bridging Deep Neural Networks and Differential Equations for Image Analysis and Beyond
报告人：董彬 副教授（ 北京大学）
报告时间： 2019 年7月2日（周二）10:30
报告地点：校本部G507
邀请人：彭亚新
报告摘要： 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 and to predict the dynamical behavior accurately. Further applications of this perspective to various problems in imaging and inverse problems will be discussed.
欢迎教师、学生参加！