DeepAI AI Chat
Log In Sign Up

N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials

by   Risi Kondor, et al.

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.


page 1

page 2

page 3

page 4


Cormorant: Covariant Molecular Neural Networks

We propose Cormorant, a rotationally covariant neural network architectu...

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

The development of efficient machine learning models for molecular syste...

Elementary superexpressive activations

We call a finite family of activation functions superexpressive if any m...

Hierarchical modeling of molecular energies using a deep neural network

We introduce the Hierarchically Interacting Particle Neural Network (HIP...

Reinforced dynamics for enhanced sampling in large atomic and molecular systems. I. Basic Methodology

A new approach for efficiently exploring the configuration space and com...

Covariance Plasticity and Regulated Criticality

We propose that a regulation mechanism based on Hebbian covariance plast...