Recent advance in machine learning for partial differential equation

Machine learning method has been applied to solve different kind of problems in different areas due to the great success in several tasks such as computer vision, natural language processing and robotic in recent year. In scientific computing community, it is well-known that solving partial differential equations, which are naturally derived from physical rules that describe some of phenomena, is a challenging task in terms of computational efficiency and model accuracy. On the other hand, machine learning models are data-driven that purely reply on learning the pattern of the data distribution. Researcher recently proposed a few new frameworks to solve certain kind of partial differential equations with machine learning technique. In this paper, we discuss two newly developed machine learning based methods for solving partial differential equations.