当前位置: 首 页 - 科学研究 - 学术报告 - 正文

bat365在线平台、所2023年系列学术活动(第026场):闫亮 副教授 东南大学

发表于: 2023-04-25   点击: 

报告题目: Failure-informed adaptive sampling for PINNs

报 告 人:闫亮 副教授 单位名称 东南大学

报告时间:2023年5月5日 15:30-16:30

报告地点:腾讯会议 ID:500-921-275

会议链接:https://meeting.tencent.com/dm/yfHVaEcmzUWg

校内联系人:刁怀安 diao @ jlu.edu.cn


报告摘要: Physics-informed neural networks (PINNs) have emerged as an effective technique for solving PDEs in a wide range of domains. Recent research has demonstrated, however, that the performance of PINNs can vary dramatically with different sampling procedures, and that using a fixed set of training points can be detrimental to the convergence of PINNs to the correct solution. In this talk, we present an adaptive approach termed failure-informed PINNs(FI-PINNs), which is inspired by the viewpoint of reliability analysis. The basic idea is to define a failure probability by using the residual, which represents the reliability of the PINNs. With the aim of placing more samples in the failure region and fewer samples in the safe region, FI-PINNs employs a failure-informed enrichment technique to incrementally add new collocation points to the training set adaptively. When compared to the conventional PINNs method and the residual-based adaptive refinement method, the developed algorithm can significantly improve accuracy, especially for low regularity and high-dimensional problems.


报告人简介:闫亮,副教授、博士生导师。主要从事不确定性量化、贝叶斯反问题理论与算法的研究。2017年入选江苏省高校“青蓝工程”优秀青年骨干教师培养对象,2018年入选东南大学首批“至善青年学者”(A层次)支持计划。2019年在全国反问题年会上获得“优秀青年学术奖”。已经在《SIAM J. Sci. Comput.》、《Inverse Problems》、《J. Comput. Phys.》等国内外刊物上发表30多篇学术论文。