Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning
arXiv:2109.13901
Abstract
Integrating physical inductive biases into machine learning can improve model generalizability. We generalize the successful paradigm of physics-informed learning (PIL) into a more general framework that also includes what we term physics-augmented learning (PAL). PIL and PAL complement each other by handling discriminative and generative properties, respectively. In numerical experiments, we show that PAL performs well on examples where PIL is inapplicable or inefficient.
arXiv comment10 pages, 3 figures, 4 tables
References in corpus (11)
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Neural Ordinary Differential Equations
- Group Equivariant Convolutional Networks
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
- Do Vision Transformers See Like Convolutional Neural Networks?
- E(n) Equivariant Graph Neural Networks
- AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
- Lagrangian Neural Networks
- Learning Neural PDE Solvers with Convergence Guarantees
- Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network