Hamiltonian Generative Networks

09/30/2019
by   Peter Toth, et al.
0

The Hamiltonian formalism plays a central role in classical and quantum physics. Hamiltonians are the main tool for modelling the continuous time evolution of systems with conserved quantities, and they come equipped with many useful properties, like time reversibility and smooth interpolation in time. These properties are important for many machine learning problems - from sequence prediction to reinforcement learning and density modelling - but are not typically provided out of the box by standard tools such as recurrent neural networks. In this paper, we introduce the Hamiltonian Generative Network (HGN), the first approach capable of consistently learning Hamiltonian dynamics from high-dimensional observations (such as images) without restrictive domain assumptions. Once trained, we can use HGN to sample new trajectories, perform rollouts both forward and backward in time and even speed up or slow down the learned dynamics. We demonstrate how a simple modification of the network architecture turns HGN into a powerful normalising flow model, called Neural Hamiltonian Flow (NHF), that uses Hamiltonian dynamics to model expressive densities. We hope that our work serves as a first practical demonstration of the value that the Hamiltonian formalism can bring to deep learning.

READ FULL TEXT
research
07/28/2020

Mastering high-dimensional dynamics with Hamiltonian neural networks

We detail how incorporating physics into neural network design can signi...
research
01/31/2022

Learning Hamiltonians of constrained mechanical systems

Recently, there has been an increasing interest in modelling and computa...
research
04/11/2022

Learning Trajectories of Hamiltonian Systems with Neural Networks

Modeling of conservative systems with neural networks is an area of acti...
research
07/08/2022

Continuous Methods : Hamiltonian Domain Translation

This paper proposes a novel approach to domain translation. Leveraging e...
research
11/10/2021

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision

A recently proposed class of models attempts to learn latent dynamics fr...
research
05/31/2023

Parameterized Wasserstein Hamiltonian Flow

In this work, we propose a numerical method to compute the Wasserstein H...
research
07/19/2020

Machine Learning a Molecular Hamiltonian for Predicting Electron Dynamics

We develop a mathematical method to learn a molecular Hamiltonian from m...

Please sign up or login with your details

Forgot password? Click here to reset