首页 - 学术活动The Kolmogorov Superposition Theorem (KST, 1957), offers a mathematically elegant framework for expressing any high-dimensional continuous function as a superposition of lower-or one-dimensional continuous functions. This foundational theorem has recently gained renewed interest, particularly in neural networks. However, a major challenge remains: the one-dimensional functions resulting from all constructions are highly non-smooth. In this talk, we present a novel approximate version of Kolmogorov superpositions involving C2 inner functions and piecewise C2 outer functions and show its applications in neural network approximations. This talk will be based on joint works with L. Song (Lanzhou University), Z. Chen & Z. Wang (NTU), and J. Toscane & G. Karniadakis (Brown University).
报告人简介:王立联,新加坡南洋理工大学正教授。2000年获上海大学计算数学博士学位。 2002至2005年,在美国普渡大学(Purdue University)从事博士后研究工作和担任访问助理教授,并于2005年底加入新加坡南洋理工大学数理学院。 2016年至2019年,受聘为厦门大学闽江讲座教授。长期从事高精度数值方法及其应用研究,在《Appl. Comput. Harmonic Anal.》、《SIAM J. Numer. Anal.》、《SIAM J. Sci. Comp.》、《SIAM J. Appl. Math》、《Math. Comp.》、 《Journal of Differential Equations》、《Automatica》、《IEEE Transaction on Image Processing》等国际计算和应用数学顶级学术期刊上发表学术论文120余篇,并由Springer-Verlag出版社出版学术专著1部《Spectral Methods, 2011》(合著), 和英国剑桥大学出版社学术专著1部《Spectral and Spectral Element Methods for Fractional Ordinary and Partial Differential Equations, 2024》(合著)。
注:本报告由数学科学全国重点实验室开放课题SLMS-2025-KFKT-TD-11组织。