基于分层嵌套基的多尺度神经网络
A multiscale neural network based on hierarchical nested bases
AI总结:
本文提出一种基于快速多极子方法和H²矩阵中分层嵌套基思想的多尺度人工神经网络,用于高效近似高维非线性映射,该方法在参数空间维度线性增长的情况下减少参数数量,通过非线性薛定谔方程、辐射转移方程和Kohn-Sham映射的求解来验证其性能。
摘要:
近年来,深度学习在许多领域取得了显著成果。本文介绍了一种基于快速多极子方法和H²矩阵中分层嵌套基思想的多尺度人工神经网络,用于高维非线性映射。该方法允许我们高效近似来自偏微分方程或积分方程的离散非线性映射。它也自然扩展了我们最近基于分层矩阵一般化的工作[Fan et al. arXiv:1807.01883],但参数数量更少。特别是,神经网络的参数数量与离散PDE参数空间的维度成线性增长。我们通过近似非线性薛定谔方程、辐射转移方程和Kohn-Sham映射的解映射来展示该架构的性质。
英文摘要:
In recent years, deep learning has led to impressive results in many fields. In this paper, we introduce a multi-scale artificial neural network for high-dimensional non-linear maps based on the idea of hierarchical nested bases in the fast multipole method and the $\mathcal{H}^2$-matrices. This approach allows us to efficiently approximate discretized nonlinear maps arising from partial differential equations or integral equations. It also naturally extends our recent work based on the generalization of hierarchical matrices [Fan et al. arXiv:1807.01883] but with a reduced number of parameters. In particular, the number of parameters of the neural network grows linearly with the dimension of the parameter space of the discretized PDE. We demonstrate the properties of the architecture by approximating the solution maps of non-linear Schr{ö}dinger equation, the radiative transfer equation, and the Kohn-Sham map.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。