Lawrence Berkeley National Laboratory
Euclidean Symmetry and Equivariance in Machine Learning
- Author(s): Smidt, TE
- et al.
Published Web Locationhttps://doi.org/10.1016/j.trechm.2020.10.006
© 2020 Elsevier Inc. Understanding the role of symmetry in the physical sciences is critical for choosing an appropriate machine-learning method. While invariant models are the most prevalent symmetry-aware models, equivariant models such as Euclidean neural networks more faithfully represent physical interactions and are ready to take on challenges across the physical sciences.