Solving the Bose-Hubbard model with machine learning

Abstract

Motivated by the recent successful application of artificial neural networks to quantum many-body problems [G. Carleo and M. Troyer, Science {\bf 355}, 602 (2017)], a method to calculate the ground state of the Bose-Hubbard model using a feedforward neural network is proposed. The results are in good agreement with those obtained by exact diagonalization and the Gutzwiller approximation. The method of neural-network quantum states is promising for solving quantum many-body problems of ultracold atoms in optical lattices.

4 pages, 4 figures

References in corpus (4)

• Learning phase transitions by confusion
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems

Cited by in corpus (3)

• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Phase Diagrams of Three-Dimensional Anderson and Quantum Percolation Models using Deep Three-Dimensional Convolutional Neural Network