Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network

no code implementations • 26 Jan 2022 • Pengpeng Shi, Zhi Zeng, Tianshou Liang

Different from "deep" fully-connected neural networks embedded with physical information (PINN), a novel shallow framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective, in which the physical field is generated by a deconvolution layer and a single convolution layer.

Physics-informed machine learning