报告题目:Solving an inverse source problem by deep neural network method with convergence and error analysis
报 告 人:刘继军 教授
所在单位:东南大学
报告时间:2022年11月3日 星期四 下午14:00-15:00
报告地点:腾讯会议 ID:939-312-800 密码:3359
会议链接:https://meeting.tencent.com/dm/fIrxzuOBE2Rw
校内联系人:张德悦 dyzhang@jlu.edu.cn
报告摘要:For the inverse source problem of an elliptic system using noisy internal measurement as inversion input, we approximate its solution by the neural network function, which is yielded by optimizing an empirical loss function with some regularizing terms. We analyze the convergence of the general loss with noisy input in Deep Galerkin Method by the regularizing empirical loss function. Based on the upper bound of the expected loss function by its regularizing empirical form, we establish the upper bound of the expected loss function at the minimizer of regularizing empirical noisy loss function in terms of the number of sampling points well as the noise level quantitatively, for suitably chosen regularizing parameters and regularizing terms. Then, by specifying the number of sampling points in terms of noise level of inversion input data, we establish the error orders representing the difference between the neural network solution and the exact one, under some {\it a-priori} restrictions on the source. Finally, we give numerical implementations for several examples to verify our theoretical results. This is a joint work with Dr. Hui Zhang.
报告人简介:刘继军,男,1965年出生,博士。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等多项基金项目。已在SIAM J., Inverse Problems等发表学术论文130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。入选江苏省青蓝工程青年骨干教师,青蓝工程中青年学术带头人,江苏省333工程第三层次培养人选。获宝钢教育基金会全国优秀教师一等奖,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。