报告题目：A Phase Shift Deep Neural Network for High Frequency Problems

主 讲 人：李筱光

单 位：湖南师范大学

时 间：11月24日9:30

腾 讯 ID：591 368 560

摘 要：

Deep neural network(DNN) is shown converges faster in low frequencies. Taking advantage of this fact, we propose a phase shift deep neural network (PhaseDNN) for a frequency uniform convergence in approximating high frequency functions and solutions of wave equations. PhaseDNN constructs a series of moderately-sized DNNs for selected high frequency ranges. With the help of phase shifts in the frequency domain, each of the trained DNNs can approximate a function’s specific high frequency range at the speed of low frequency learning. The PhaseDNN is then applied to learn the solution of high frequency wave problems in inhomogeneous media through the least square residuals of either differential or integral equations.

简 介：

李筱光，男，本科、博士毕业于北京大学，曾在北京计算科学研究中心、美国南卫理公会大学从事博士后及访问学者，目前任职于湖南师范大学数学与统计学院。研究领域包括随机模拟、稀有事件的计算和模拟、深度学习在科学计算中的应用。在SIAM J. Math. Anal.，SIAM J. Sci. Comput，Multiscale Model. Simul. PLOS Comput. Biol等期刊发表论文。