Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe

Abstract

A method for machine learning and serving of discrete field theories in physics is developed. The learning algorithm trains a discrete field theory from a set of observational data on a spacetime lattice, and the serving algorithm uses the learned discrete field theory to predict new observations of the field for new boundary and initial conditions. The approach to learn discrete field theories overcomes the difficulties associated with learning continuous theories by artificial intelligence. The serving algorithm of discrete field theories belongs to the family of structure-preserving geometric algorithms, which have been proven to be superior to the conventional algorithms based on discretization of differential equations. The effectiveness of the method and algorithms developed is demonstrated using the examples of nonlinear oscillations and the Kepler problem. In particular, the learning algorithm learns a discrete field theory from a set of data of planetary orbits similar to what Kepler inherited from Tycho Brahe in 1601, and the serving algorithm correctly predicts other planetary orbits, including parabolic and hyperbolic escaping orbits, of the solar system without learning or knowing Newton's laws of motion and universal gravitation. The proposed algorithms are also applicable when effects of special relativity and general relativity are important. The illustrated advantages of discrete field theories relative to continuous theories in terms of machine learning compatibility are consistent with Bostrom's simulation hypothesis.

25 pages, 12 figures

References in corpus (10)

• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• On Learning Hamiltonian Systems from Data
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
• Variational integration for ideal magnetohydrodynamics with built-in advection equations
• Explicit high-order noncanonical symplectic algorithms for ideal two-fluid systems
• Toroidal regularization of the guiding center Lagrangian
• The geometric theory of charge conservation in particle-in-cell simulations
• Field theory and structure-preserving geometric particle-in-cell algorithm for drift wave instability and turbulence