Artificial Neural Network Methods in Quantum Mechanics

Abstract

In a previous article we have shown how one can employ Artificial Neural Networks (ANNs) in order to solve non-homogeneous ordinary and partial differential equations. In the present work we consider the solution of eigenvalue problems for differential and integrodifferential operators, using ANNs. We start by considering the Schrödinger equation for the Morse potential that has an analytically known solution, to test the accuracy of the method. We then proceed with the Schrödinger and the Dirac equations for a muonic atom, as well as with a non-local Schrödinger integrodifferential equation that models the $n+\alpha$ system in the framework of the resonating group method. In two dimensions we consider the well studied Henon-Heiles Hamiltonian and in three dimensions the model problem of three coupled anharmonic oscillators. The method in all of the treated cases proved to be highly accurate, robust and efficient. Hence it is a promising tool for tackling problems of higher complexity and dimensionality.

Latex file, 29pages, 11 psfigs, submitted in CPC

Cited by in corpus (46)

• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Recurrent Neural Network Wave Functions
• Perspective on integrating machine learning into computational chemistry and materials science
• Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learning
• Machine Learning for Quantum Matter
• Autoregressive Transformer Neural Network for Simulating Open Quantum Systems via a Probabilistic Formulation
• Enforcing Dirichlet boundary conditions in physics-informed neural networks and variational physics-informed neural networks
• Exotic muon-electron conversion in nuclei and R-parity violating supersymmetry
• Neural Network Study of Hidden-Charm Pentaquark Resonances
• Machine learning quantum mechanics: solving quantum mechanics problems using radial basis function networks
• Investigating Topological Order using Recurrent Neural Networks
• A Unitary Weights Based One-Iteration Quantum Perceptron Algorithm for Non-Ideal Training Sets
• Cornell Potential: A Neural Network Approach
• Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
• Robust quantum gates using smooth pulses and physics-informed neural networks
• Quasinormal modes of dS and AdS Black Holes: Feedforward neural network method
• Protocol Discovery for the Quantum Control of Majoranas by Differentiable Programming and Natural Evolution Strategies
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Enhancing approximation abilities of neural networks by training derivatives
• Hypersolvers: Toward Fast Continuous-Depth Models
• A Study of Excited ${\Omega }_b^{-}$ States in Hypercentral Constituent Quark Model via Artificial Neural Network
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• High-order matrix method with delimited expansion domain
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• Gravitational Duals from Equations of State
• Quasinormal Modes in Modified Gravity using Physics-Informed Neural Networks
• Unsupervised Neural Networks for Quantum Eigenvalue Problems
• Addressing the Non-perturbative Regime of the Quantum Anharmonic Oscillator by Physics-Informed Neural Networks
• Deep reinforcement learning for preparation of thermal and prethermal quantum states
• Meshfree Variational Physics Informed Neural Networks (MF-VPINN): an adaptive training strategy
• Energy Levels of One Dimensional Anharmonic Oscillator via Neural Networks
• Analytical derivatives of Neural Networks
• Physics-Informed Neural Networks for Nonlocal Beam Eigenvalue Problems
• Neural Network Methods for Boundary Value Problems Defined in Arbitrarily Shaped Domains
• Neural Network Solutions to Differential Equations in Non-Convex Domains: Solving the Electric Field in the Slit-Well Microfluidic Device
• Mass Spectrum of Exotic X(5568) State via Artificial Neural Network
• Avoiding overfitting of multilayer perceptrons by training derivatives
• Lepton Flavor Violation: Constraints from exotic muon to electron conversion
• Machine Learning Wavefunction
• Eig-PIELM: A Mesh-Free Approach for Efficient Eigen-Analysis with Physics-Informed Extreme Learning Machines
• Deep learning neural network for approaching Schrödinger problems with arbitrary two-dimensional confinement
• Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
• Bayesian Reasoning for Physics Informed Neural Networks