题    目：Towards universal physics-informed neural operator

主讲人：孟琪 副研究员

单    位：中国科学院

时    间：2024年8月26日 9:00

腾讯ID：105 465 972

摘    要：AI-powered scientific computing represents a paradigm shift in the realm of scientific research and computation that integrates artificial intelligence into traditional scientific computing, offering unprecedented opportunities for enhanced efficiency and accelerated scientific discovery. As the AI foundation models have achieved success in language or vision tasks, we seek the opportunity on solving partial differential equations. In this talk, we will introduce several designs of AI approaches towards universal neural operator that incorporate the physical knowledge into the AI models to enhance the efficiency and accuracy in evolving the dynamic systems governed the several partial differential equations.

简    介：孟琪，2018年于北京大学获得博士学位, 后入职微软研究院机器学习组任首席研究员（Principal Researcher），现为中国科学院数学与系统科学院副研究员。从事机器学习理论，机器学习与科学计算等方向的研究，于机器学习国际会议及期刊发表文章40余篇，长期担任ICML, Neurips, TPAMI等会议和期刊审稿人。