报告题目：Learning nonlinear functionals by deep neural networks

报告人：樊军博士，香港浸会大学

报告时间：2023年11月23日（周四）14:30-15:30

报告地点：腾讯会议：811-922-980

报告摘要：Neural networks have proven their versatility in approximating continuous functions, but their capabilities extend far beyond. In this talk, we delve into the realm of functional deep neural networks, which offer a promising approach for approximating nonlinear functionals defined on Lp spaces. By investigating the convergence rates of approximation and generalization errors under different regularity conditions, we gain insights into the theoretical properties of these networks. This analysis contributes to a deeper understanding of functional neural networks and opens up new possibilities for their effective application in diverse domains such as dynamic system identification, mean field control, and functional data analysis.

报告人简介：樊军，香港浸会大学数学系副教授。樊军博士于2013年在香港城市大学获得博士学位。2017年入职香港浸会大学数学系，2022年获终身教职。他曾于威斯康辛大学麦迪逊分校担任博士后研究员。 研究兴趣包括统计学习理论和深度学习理论。 在机器学习领域中有影响力的期刊上发表了一系列学术论文，主要包括Journal of Machine Learning Research, Applied and Computational Harmonic Analysis, Neural Networks, Journal of Fourier Analysis and Applications等。现为 Mathematical Foundations of Computing, Software Impacts, Journal of Mathematics, Frontiers in Applied Mathematics and Statistics的编委。

邀请人：向道红