Keywords
machine learning
partial differential equations
DGM
DRM
How to Cite
Abstract
Recently deep learning networks made huge progress due to the advances in highperformance computing technologies. This study covers a range of approaches to solving partial differential equations with deep learning. An example of solving the Poisson equation in a twodimensional domain using the Galerkin method with deep neural networks is presented.
References
Бетелин В. Б., Галкин В. А. Универсальные вычислительные алгоритмы и их обоснование для приближенного решения дифференциальных уравнений. Доклады Академии наук. 2019;488(4):351–357. DOI: https://doi.org/10.31857/S0869-56524884351-357.
Колмогоров А. Н. О представлении непрерывных функций нескольких переменных в виде суперпозиций непрерывных функций одного переменного и сложения. Доклады Академии наук СССР. 1957;114(5):953–956.
Hecht-Nielsen R. Kolmogorov's Mapping Neural Network Existence Theorem. Proceedings of the International Conference on Neural Networks. NewYork: IEEE Press. 1987. III:11-14.
Funahashi K. On the Approximate Realization of Continuous Mappings by Neural Networks. Neural Networks. 1989;2(3):183-192.
Cybenko G. Approximation by Superposition of a Sigmoidal Function. Mathematics of Control, Signals, and Systems. 1989;2:303-314.
Sirignano J., Spiliopoulos K. DGM: A Deep Learning Algorithm for Solving Partial Differential Equations. Available at: arXiv:1708.07469.
Weinan E, Bing Yu. The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational Problems. Available at: https://arxiv.org/pdf/1710.00211.pdf.
Wang Z., Zhang Z. A Mesh-Free Method for Interface Problems Using the Deep Learning Approach. Available at: https://arxiv.org/pdf/1901.00618.pdf.
Chen J., Viquerat J., Hachem E. U-net Architectures for Fast Prediction of Incompressible Laminar Flows. Available at: https://arxiv.org/pdf/1910.13532.pdf.
Liu Y., Dinh N. Sato Y., Niceno B. Data-Driven Modeling for Boiling Heat Transfer: Using Deep Neural Networks and High-Fidelity Simulation Results. Available at: https://arxiv.org/pdf/1808.01859.pdf.
Tompson J., Schlachter K., Sprechmann P., Perlin K. Accelerating Eulerian Fluid Simulation With Convolutional Networks. Available at: https://arxiv.org/pdf/1607.03597.pdf.
Miyanawala T. P., Jaiman R. K. An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics. Available at: https://arxiv.org/pdf/1710.09099.pdf.