题目:Barron Type Spaces and the Application To Neural Network Approximation
报告人:明平兵研究员(中科院数学与系统科学研究院)
邀请人:沈晓芹教授 (beat365官方最新版数学系)
报告时间:2023年4月16日下午4:00-5:30
报告地点:教九楼beat365官方最新版会议室9-320
摘要:We shall discuss various Barron type spaces arising from neural network. The relations among them will be clarified, and we shall also establish the relationship between Barron type spaces and the classical function spaces such as Besov space, Sobolev space and Bessel potential space. As an application, certain new approximation results for the shallow neural network and deep neural network with the Barron class as the target function space will be proved. This is a joint work with Yulei Liao (AMSS, CAS) and Yan Meng (RUC).
报告人简介:明平兵,国家杰出青年基金获得者,中国科学院数学与系统科学研究院研究员,科学与工程计算国家重点实验室副主任,主要从事固体多尺度建模、模拟及多尺度算法的研究。他预测了石墨烯的理想强度并在Cauchy-Born法则的数学理论、拟连续体方法的稳定性方面有较为系统的工作。他在JAMS, CPAM, ARMA, PRB, JMPS,Acta Materialia,SINUM, Math. Comp. Numer. Math等国际著名学术期刊上发表学术论文六十余篇。他曾应邀在SCADE2009,The SIAM Mathematics Aspects of Materials Science 2016等会议上作大会报告。明平兵于2014年获得国家杰出青年基金,并于2019年入选第四批国家“万人计划”中青年科技创新领军人才计划。