瑞士工程科学院院士 Michael Unser 教授给我院师生做学术报告

发布者:杨淳沨发布时间:2021-05-17浏览次数:13

各位老师好:


应影像实验室邀请,520日(周四 )晚上19:00-20:30瑞士工程科学院院士 Michael Unser 教授给我院师生做学术报告,具体情况如下:


报告题目:样条曲线与成像:从压缩感知到深度神经网络
Splines and imaging: From compressed sensing to deep neural networks

报告人:Michael Unser,洛桑联邦理工学院教授,瑞士工程科学院院士

主持人:Jean-Louis Coatrieux,东南大学特聘教授,INSERM主任研究员

报告时间:2021年5月20日,19:00-20:30

报告地点:四牌楼校区中山院111,

  

参会链接:zoom会议ID:924 7137 0780

密码:576144

https://univ-rennes1-fr.zoom.us/j/92471370780

报告摘要:

  

We present theoretical arguments that support the use of splines for the resolution of inverse problems in imaging as well as for the design of deep neural networks. The foundation is a representer theorem that characterizes the solution set of a broad class of linear inverse problems with generalized total-variation regularization. The primary solutions are non-uniform splines whose type is matched to the underlying regularization operator; these splines are intrinsically sparse, and hence compatible with the kind of formulation (and algorithms) used in compressed sensing.We then make the link with current learning techniques by applying the theorem to optimize the shape of individual activations in a deep neural network. By selecting the regularization functional to be the 2nd-order total variation, we obtain an “optimal” deep-spline network whose activations are piecewise-linear splines with a few adaptive knots. Since each spline knot can be encoded with a ReLU unit, this provides a variational justification of the popular ReLU architecture. It also suggests some new computational challenges for the determination of the optimal activations involving linear combinations of ReLUs.

报告人简介:

  

Michael Unser is professor and director of EPFL's Biomedical Imaging Group, Lausanne, Switzerland. His primary area of investigation is biomedical image processing. He is internationally recognized for his research contributions to sampling theory, wavelets, the use of splines for image processing, stochastic processes, and computational bioimaging. He has published over 350 journal papers on those topics. He is the author with P. Tafti of the book An introduction to sparse stochastic processes, Cambridge University Press 2014. From 1985 to 1997, he was with the Biomedical Engineering and Instrumentation Program, National Institutes of Health, Bethesda USA, conducting research on bioimaging. Dr. Unser has served on the editorial board of most of the primary journals in his field including the IEEE Transactions on Medical Imaging (associate Editor-in-Chief 2003-2005), IEEE Trans. Image Processing, Proc. of IEEE, and SIAM J. of Imaging Sciences. He is the founding chair of the technical committee on Bio Imaging and Signal Processing (BISP) of the IEEE Signal Processing Society. Prof. Unser is a fellow of the IEEE (1999), an EURASIP fellow (2009), and a member of the Swiss Academy of Engineering Sciences. He is the recipient of several international prizes including five IEEE-SPS Best Paper Awards, two Technical Achievement Awards from the IEEE (2008 SPS and EMBS 2010) and the 2020 EMBS Academic Career Achievement Award.