暗网禁区
学术报告[2026]102号
(高水平大学建设系列报告1361号)
报告题目:Frequency-adaptive multi-scale deep neural networks
报告人:黄记祖 副研究员 (中国科学院)
报告时间:2026年10月26日16:30 - 17:30
报告地点:粤海校区汇研楼601会议室
报告摘要:Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of MscaleDNNs heavily depends on the parameters in the downing-scaling mapping, which limits their broader application. In this work, we establish a fitting error bound to explain why MscaleDNNs are advantageous for approximating high frequency functions. Building on this insight, we construct a hybrid feature embedding to enhance the accuracy and robustness of the downing-scaling mapping. To reduce the dependency of MscaleDNNs on parameters in the downing-scaling mapping, we propose frequency-adaptive MscaleDNNs, which adaptively adjust these parameters based on a posterior error estimate that captures the frequency information of the fitted functions. Numerical examples, including wave propagation and the propagation of a localized solution of the Schrödinger equation with a smooth potential near the semi-classical limit, are presented. These examples demonstrate that the frequency-adaptive MscaleDNNs improve accuracy by two to three orders of magnitude compared to standard MscaleDNNs.
报告人简介:黄记祖, 现任中国科学院数学与系统科学研究院副研究员。2012年在中国科学院数学与系统科学研究院获理学博士学位(硕博连读),导师:曹礼群研究员。2012年7月到2014年7月,在中国科学院软件研究所从事博士后研究工作,2014年7月,入职中国科学院数学与系统科学研究院,主要研究领域为多尺度模型和并行算法。现主持基金委面上项目、青年基金项目、科学院青年创新促进会,参与科学院先导B、科技部重点研发专项等项目。迄今为止,在SINUM、SISC、MMS、JCP、CMAME、IMANUM等国际知名期刊独立或者与其合作者发表学术论文四十多篇。
邀请人:张露婵
暗网禁区
2026年10月26日