CBMS Conference: Deep Learning and Numerical Partial Differential Equations

该奖项为将于2023年6月19日至24日在巴尔的摩摩根州立大学举行的“深度学习和数值偏微分方程”数学科学会议会议委员会提供支持。本次会议将汇集来自数学、计算机科学和工程领域的专家，讨论涉及深度学习和数值偏微分方程（PDEs）的主题。因此，它将为专家和年轻研究人员提供一个教育平台和论坛，以交流理论和应用发展的新进展。理论和应用专家之间的互动旨在激发新的想法和合作项目。会议将资助大约30名参与者，特别是研究生、博士后助理、早期职业研究人员和来自代表性不足群体的个人。会议旨在为与会者提供学习深度学习的基础数学理论，交流潜在的重要研究方向，讨论可能的实际应用，并与领先的研究人员互动的绝佳机会。杰出的首席讲师将是宾夕法尼亚州立大学的凡尔纳·m·威拉曼教授徐金超。讲座将介绍深度学习理论和应用的最新发展，连接两个不同领域的模型和算法：(1)机器学习，包括逻辑回归和深度神经网络；(2)数值偏微分方程，包括有限元和多网格方法。该系列讲座建立在对机器学习模型和算法的最新发展的讨论之上，并向会议参与者展示了内在关联主题的前沿研究。因此，本次会议有望为深度学习的理解带来新的见解，并进一步促进其在不同科学和工程领域的分析和应用。欲了解更多信息，请参阅会议网页：https://sites.google.com/view/nsf-cbms-dl-nmpde/homeThis该奖项反映了美国国家科学基金会的法定使命，并通过基金会的智力价值和更广泛的影响审查标准进行评估，认为值得支持。

This award provides support for the Conference Board of the Mathematical Sciences conference "Deep Learning and Numerical PDEs," to be held at Morgan State University in Baltimore, June 19-24, 2023. This conference will bring together experts from mathematics, computer science, and engineering on topics involving deep learning and numerical partial differential equations (PDEs). As such, it will provide an education platform and forum for experts and young researchers to communicate new advancements in theoretical and application developments. The interaction between theory and application experts is intended to spark new ideas and collaborative projects. The conference will fund approximately 30 participants, especially graduate students, postdoctoral associates, early-career researchers, and individuals from underrepresented groups. The meeting aims to provide extraordinary opportunities to the participants to study the fundamental mathematical theory of deep learning, communicate potential important research directions, discuss possible practical applications, and interact with leading researchers. The distinguished principal lecturer will be Verne M. Willaman Professor Jinchao Xu of Pennsylvania State University. The lectures will present the latest developments on the theory and applications of deep learning, bridging models and algorithms from two different fields: (1) machine learning, including logistic regression and deep neural networks, and (2) numerical PDEs, including finite element and multigrid methods. The lecture series builds upon a discussion on the latest developments in machine learning models and algorithms and presents cutting-edge research on intrinsically connected topics to the participants of the conference. As a result, this conference is expected to bring novel insights into the understanding of deep learning, and to further promote their analysis and applications in different scientific and engineering fields. For more information, please refer to the conference webpage: https://sites.google.com/view/nsf-cbms-dl-nmpde/homeThis award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.