清华主页 EN
导航菜单

Learning constitutive models with neural networks

来源: 12-29

时间:2022-12-29 Thu 14:00-16:00

地点: Venue: 1129B Zoom: 537 192 5549(PW: BIMSA)

组织者:Wuyue Yang, Fansheng Xiong, Xiaopei Jiao

主讲人: Fansheng Xiong BIMSA

Abstract

In this talk, I will introduce some work of learning constitutive equations in fluid mechanics and geophysics based on machine learning


Speaker Intro

熊繁升,现任北京雁栖湖应用数学研究院助理研究员,曾任北京应用物理与计算数学研究所所聘博士后。先后毕业于中国地质大学(北京)、清华大学,美国耶鲁大学联合培养博士。研究兴趣主要集中于基于机器学习算法(DNN、PINN、DeepONet等)求解微分方程模型正/反问题及其在地球物理波传播问题中的应用,相关成果发表在JGR Solid Earth、GJI、Geophysics等期刊上。

返回顶部
相关文章
  • Learning Nonlocal Constitutive Models with Neural Operators

    AbstractConstitutive models are widely used for modeling complex systems in science and engineering, when first-principle-based, well-resolved simulations are prohibitively expensive. For example, in fluid dynamics, constitutive models are required to describe nonlocal, unresolved physics such as turbulence and laminar-turbulent transition. However, traditional constitutive models based on PDEs...

  • Mean-field theory of learning dynamics in deep neural networks

    AbstractLearning dynamics of deep neural networks is complex. While previous approaches made advances in mathematical analysis of the dynamics of two-layer neural networks, addressing deeper networks have been challenging. In this talk, I will present a mean field theory of the learning dynamics of deep networks and discuss its practical implications