Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In this paper we propose a generalization of this work that generally exhibits improved performace, but from an implementation point of view is actually simpler. An unusual feature of the proposed architecture is that it uses the Clebsch--Gordan transform as its only source of nonlinearity, thus avoiding repeated forward and backward Fourier transforms. The underlying ideas of the paper generalize to constructing neural networks that are invariant to the action of other compact groups.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In …
Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
$E(3)$-equivariant neural networks have proven to be effective in a wide range of 3D modeling tasks. A fundamental operation of such networks is the tensor product, which allows interaction between different feature type…
Cormorant: Covariant Molecular Neural Networks
We propose Cormorant, a rotationally covariant neural network architecture for learning the behavior and properties of complex many-body physical systems. We apply these networks to molecular systems with two goals: lear…
Clebsch-Gordan Transformer: Fast and Global Equivariant Attention
The global attention mechanism is one of the keys to the success of transformer architecture, but it incurs quadratic computational costs in relation to the number of tokens. On the other hand, equivariant models, which …
Point Cloud ClassificationData AugmentationRobotic GraspingN-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
We describe N-body networks, a neural network architecture for learning the behavior and properties of complex many body physical systems. Our specific application is to learn atomic potential energy surfaces for use in …