报告题目:On stability and regularization for data-driven solution of parabolic inverse source problems
报 告 人:刘继军,东南大学
报告摘要:The inverse source problems for diffusion process are of great importance, with the aim of recovering the internal source by some extra information about the physical field. There already exist considerable work on these topics including the regularizing schemes as well as the recovering scheme. In this talk, we will consider an inverse problem of recovering the spatial dependent ingredient of the internal source from final measurement data based on the neural network framework, where both the unknown source and the temperature filed are represented by two networks separately. The penalty terms containing the control equation is introduced into the loss function, and consequently the error estimate for the reconstructed solution are derived.
报告人简介:刘继军,东南大学二级教授,博士生导师,享受国务院政府特殊津贴专家。现任南京应用数学中心常务副主任,全国大学生数学建模竞赛组委会委员,中国工业与应用数学学会数学建模竞赛专业委员会委员,江苏省计算数学学会副理事长。国家精品资源共享课《数学建模与数学实验》主持人。历任中国工业与应用数学学会常务理事,中国计算数学学会常务理事,江苏省工业与应用数学学会第五届、第六届理事会理事长。长期从事数学物理反问题、大规模科学计算和介质成像的数学理论和方法的研究。主持完成国家自然科学基金重大研究计划培育项目、面上项目、国际合作项目等项目。已在SIAM J. Appl. Math等刊物发表学术论文100余篇,在科学出版社出版学术专著2本。曾受中国NSFC、德国DAAD、韩国21Brain Project等资助赴国外开展合作研究。2012-2017年任Inverse Problems in Sciences and Engineering编委,2018年起任J. Inverse and Ill-posed Problems编委。作为主持人获江苏省教学成果一等奖、江苏省自然科学三等奖、教育部自然科学二等奖。
报告时间:2023年4月17日14:00
报告地点:文渊楼B434
主办单位:伟德国际1946源自英国