学术报告
学术报告
当前位置:首页  学术报告
中国科学院数学与系统科学研究院张波研究员报告通知
发布人:张艺芳  发布时间:2024-12-02   浏览次数:10

 

报告人:张波研究员

报告题目:Kernel Machine and Inverse Scattering Problems

报告摘要:In this talk we connect machine learning techniques, in particular, kernel machine learning, to inverse source and scattering problems. We show the proposed kernel machine learning has demonstrated generalization capability and has a rigorous mathematical foundation. The proposed learning is based on the Mercer kernel, the reproducing kernel Hilbert space, the kernel trick, as well as the mathematical theory of inverse source and scattering theory, and the restricted Fourier integral operator. The kernel machine learns a multi-layer neural network which outputs an $\epsilon$-neighborhood average of the unknown or its nonlinear transformation. We then apply the general architecture to the multi-frequency inverse source problem for a fixed observation direction and the Born inverse medium scattering problem. We establish mathematically justified kernel machine indicator with demonstrated capability in both shape identification and parameter identification, under very general assumptions on the physical unknown. More importantly, stability estimates are established in the case of both noiseless and noisy measurement data. Of central importance is the interplay between a restricted Fourier integral operator and a corresponding Sturm-Liouville differential operator. Several numerical examples are presented to demonstrate the capability of the proposed kernel machine learning.

报告时间:2024124  15:00-16:30

报告形式:腾讯会议,会议号:825-259-065

 

报告人简介:张波,1983年毕业于山东大学数学系,1985年在西安交通大学获硕士学位,1992年在英国斯特拉斯克莱德(Strathclyde)大学获博士学位。现任中科院数学与系统科学研究院“百人计划”研究员,中国工业与应用数学学会秘书长、大数据与人工智能专委会副主任、反问题与成像专委会副主任。2003-2007任英国Coventry大学应用数学教授,2004年通过中科院“百人计划”回国。在波传播与散射、反问题与成像、机器学习与智能数据分析的理论和算法方面进行了系统研究,在国际重要学术期刊发表论文150余篇,得到了众多同行的引用和正面评价。曾任中科院数学与系统科学研究院应用数学研究所副所长,2019年反问题国际联合会Calderon奖委员会成员,国际著名SCI期刊《IEEE Transactions on Cybernetics》编委(2012-2018),反问题国际联合会东亚分会副主席(2016-2023),中国数学会常务理事。应邀在2012年第6届和2018年第9届反问题国际会议做大会特邀报告,三次获得中科院优秀导师奖(2013, 2019, 2020),2021年获中国科学院大学领雁银奖,获2022年度北京市自然科学奖二等奖(第1完成人,信息领域),中国工业与应用数学学会(CSIAM)会士。