N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
arXiv:1803.01588
Abstract
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 molecular dynamics simulations. Our architecture is novel in that (a) it is based on a hierarchical decomposition of the many body system into subsytems, (b) the activations of the network correspond to the internal state of each subsystem, (c) the "neurons" in the network are constructed explicitly so as to guarantee that each of the activations is covariant to rotations, (d) the neurons operate entirely in Fourier space, and the nonlinearities are realized by tensor products followed by Clebsch-Gordan decompositions. As part of the description of our network, we give a characterization of what way the weights of the network may interact with the activations so as to ensure that the covariance property is maintained.
References in corpus (4)
Cited by in corpus (37)
- Machine learning and the physical sciences
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
- On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
- 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
- Data-driven rogue waves and parameter discovery in the defocusing NLS equation with a potential using the PINN deep learning
- Cormorant: Covariant Molecular Neural Networks
- Differentiable Graph Module (DGM) for Graph Convolutional Networks
- Heat transport in liquid water from first-principles and deep-neural-network simulations
- Lorentz Group Equivariant Neural Network for Particle Physics
- Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
- On Learning Sets of Symmetric Elements
- Equivariant Graph Neural Networks for 3D Macromolecular Structure
- Scale-Equivariant Steerable Networks
- A General Theory of Equivariant CNNs on Homogeneous Spaces
- Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
- Theoretical Aspects of Group Equivariant Neural Networks
- On the Universality of Rotation Equivariant Point Cloud Networks
- A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
- Graph Neural Networks for IceCube Signal Classification
- Rotation-Equivariant Deep Learning for Diffusion MRI
- Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
- Frame Averaging for Invariant and Equivariant Network Design
- Geometric Prediction: Moving Beyond Scalars
- Topos and Stacks of Deep Neural Networks
- Discrete Rotation Equivariance for Point Cloud Recognition
- Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
- Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
- Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods
- A simple equivariant machine learning method for dynamics based on scalars
- DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution
- Affine Self Convolution
- Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
- Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
- Deformation Robust Roto-Scale-Translation Equivariant CNNs
- Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks
- Geometric Algebra Attention Networks for Small Point Clouds