Deep learning and the Schrödinger equation

Abstract

We have trained a deep (convolutional) neural network to predict the ground-state energy of an electron in four classes of confining two-dimensional electrostatic potentials. On randomly generated potentials, for which there is no analytic form for either the potential or the ground-state energy, the neural network model was able to predict the ground-state energy to within chemical accuracy, with a median absolute error of 1.49 mHa. We also investigate the performance of the model in predicting other quantities such as the kinetic energy and the first excited-state energy of random potentials.

References in corpus (5)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Machine learning prediction errors better than DFT accuracy
• Machine learning for many-body physics: The case of the Anderson impurity model
• Development of a Classical Force Field for the Oxidised Si Surface: Application to Hydrophilic Wafer Bonding

Cited by in corpus (66)

• Protein-Ligand Scoring with Convolutional Neural Networks
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Opportunities and Challenges for Machine Learning in Materials Science
• Deep learning for determining a near-optimal topological design without any iteration
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Machine Learning Topological Invariants with Neural Networks
• Machine Learning the Voltage of Electrode Materials in Metal-ion Batteries
• Machine-learned multi-system surrogate models for materials prediction
• Deep Learning and Density Functional Theory
• Machine Learning Configuration Interaction
• Solving frustrated quantum many-particle models with convolutional neural networks
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Classification of Machine Learning Frameworks for Data-Driven Thermal Fluid Models
• Deep Learning and AdS/CFT
• Machine Learning for Condensed Matter Physics
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Self-learning Monte Carlo with Deep Neural Networks
• Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
• Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery
• Extensive deep neural networks for transferring small scale learning to large scale systems
• Convolutional neural networks for atomistic systems
• Machine learning density functional theory for the Hubbard model
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning
• Improved machine learning algorithm for predicting ground state properties
• Probabilistic learning on manifolds constrained by nonlinear partial differential equations for small datasets
• Deep neural networks for classifying complex features in diffraction images
• Deep neural networks for direct, featureless learning through observation: the case of 2d spin models
• Supervised machine learning of ultracold atoms with speckle disorder
• Scalable neural networks for the efficient learning of disordered quantum systems
• Neural network approaches for solving Schrödinger equation in arbitrary quantum wells
• Evolutionary reinforcement learning of dynamical large deviations
• Determining electronic properties from L-edge X-ray absorption spectra of transition metal compounds with artificial neural networks
• Deep Learning-Assisted Classification of Site-Resolved Quantum Gas Microscope Images
• Nuclear mass predictions based on convolutional neural network
• Deep learning for retrieval of the internuclear distance in a molecule from interference patterns in photoelectron momentum distributions
• Reducing the Quantum Many-electron Problem to Two Electrons with Machine Learning
• Bridging the reality gap in quantum devices with physics-aware machine learning
• Visualizing Neural Network Developing Perturbation Theory
• Physically interpretable machine learning algorithm on multidimensional non-linear fields
• Determination of impact parameter in high-energy heavy-ion collisions via deep learning
• Prospects of reinforcement learning for the simultaneous damping of many mechanical modes
• A Bird's-Eye View of Naming Game Dynamics: From Trait Competition to Bayesian Inference
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• Generation of Bose-Einstein Condensates' Ground State Through Machine Learning
• Transfer learning, alternative approaches, and visualization of a convolutional neural network for retrieval of the internuclear distance in a molecule from photoelectron momentum distributions
• Deep learning methods for the computation of vibrational wavefunctions
• Automated Design using Neural Networks and Gradient Descent
• Learning Potentials of Quantum Systems using Deep Neural Networks
• Insights into one-body density matrices using deep learning
• Deep learning approach in multi-scale prediction of turbulent mixing-layer
• How machine learning conquers the unitary limit
• A Neural Network Perturbation Theory Based on the Born Series
• Solution of inverse problem for Gross-Pitaevskii equation with artificial neural networks
• A machine learning approach to predict L-edge x-ray absorption spectra of light transition metal ion compounds
• Observing how deep neural networks understand physics through the energy spectrum of one-dimensional quantum mechanics
• Adapting reservoir computing to solve the Schrödinger equation
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Deep learning neural network for approaching Schrödinger problems with arbitrary two-dimensional confinement
• Machine-learning semi-local density functional theory for many-body lattice models at zero and finite temperature
• Weakly-supervised learning on Schrodinger equation
• Challenges and opportunities in the supervised learning of quantum circuit outputs
• Quantum carpets from Gaussian sum theory
• Algebraically-Informed Deep Networks (AIDN): A Deep Learning Approach to Represent Algebraic Structures
• Learning the gravitational force law and other analytic functions