Machine Learning Topological Invariants with Neural Networks

Abstract

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

6 pages, 4 figures and 1 table + 2 pages of supplemental material

References in corpus (24)

• Classification of topological insulators and superconductors in three spatial dimensions
• Learning phase transitions by confusion
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Deep learning and the Schrödinger equation
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Fidelity-based Probabilistic Q-learning for Control of Quantum Systems
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Probing many-body localization with neural networks
• Machine learning for many-body physics: The case of the Anderson impurity model
• Kernel methods for interpretable machine learning of order parameters
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Self-Learning Monte Carlo Method in Fermion Systems
• Self-Learning Determinantal Quantum Monte Carlo Method
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Quantum phase recognition via unsupervised machine learning
• Principal Component Analysis for Fermionic Critical Points
• Recommender Engine for Continuous Time Quantum Monte Carlo Methods
• Machine learning for many-body physics: efficient solution of dynamical mean-field theory

Cited by in corpus (137)

• Machine learning and the physical sciences
• Identifying topological order through unsupervised machine learning
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Constructing neural stationary states for open quantum many-body systems
• Unsupervised machine learning and band topology
• Novelty Detection Meets Collider Physics
• Quantum Adversarial Machine Learning
• Controlling mass and energy diffusion with metamaterials
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Deep Learning for Feynman's Path Integral in Strong-Field Time-Dependent Dynamics
• Machine learning of phase transitions in the percolation and XY models
• Unsupervised phase discovery with deep anomaly detection
• Solving frustrated quantum many-particle models with convolutional neural networks
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Unsupervised Manifold Clustering of Topological Phononics
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Cellular automata as convolutional neural networks
• Machine Learning for Condensed Matter Physics
• Unsupervised machine learning of topological phase transitions from experimental data
• Parameter diagnostics of phases and phase transition learning by neural networks
• Deep Learning Topological Invariants of Band Insulators
• Self-learning Monte Carlo with Deep Neural Networks
• Probing hidden spin order with interpretable machine learning
• Automatic spin-chain learning to explore the quantum speed limit
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Information Scrambling in Quantum Neural Networks
• Machine learning action parameters in lattice quantum chromodynamics
• Real space mapping of topological invariants using artificial neural networks
• 2024 roadmap on 2D topological insulators
• Learning entropy production via neural networks
• Physical Symmetries Embedded in Neural Networks
• Smallest Neural Network to Learn the Ising Criticality
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Mapping the Design Space of Photonic Topological States via Deep Learning
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Topological thermal transport
• Automated discovery of characteristic features of phase transitions in many-body localization
• Matrix Product Operators for Sequence to Sequence Learning
• Unsupervised Learning of Non-Hermitian Topological Phases
• Machine Learning of Frustrated Classical Spin Models. II. Kernel Principal Component Analysis
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Machine learning topological phases in real space
• Interpreting machine learning of topological quantum phase transitions
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Far-field subwavelength acoustic imaging by deep learning
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Machine learning topological invariants of non-Hermitian systems
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Topological Persistence Machine of Phase Transitions
• Deep neural networks for classifying complex features in diffraction images
• Identifying Topological Phase Transitions in Experiments Using Manifold Learning
• Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions
• Machine learning spectral indicators of topology
• Quantum topology identification with deep neural networks and quantum walks
• Unsupervised learning using topological data augmentation
• Phase Detection with Neural Networks: Interpreting the Black Box
• Deep learning of topological phase transitions from entanglement aspects
• Reinforcement-learning-based control of convectively-unstable flows
• Phase transition encoded in neural network
• Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
• Self-organizing maps as a method for detecting phase transitions and phase identification
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• Rapid Exploration of Topological Band Structures using Deep Learning
• A Neural Networks study of the phase transitions of Potts model
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• Application of Convolutional Neural Network to Quantum Percolation in Topological Insulators
• Machine prediction of topological transitions in photonic crystals
• Learning quantum phase transitions through Topological Data Analysis
• Interpretable Conservation Law Estimation by Deriving the Symmetries of Dynamics from Trained Deep Neural Networks
• Machine learning non-Hermitian topological phases
• Applications of deep learning to relativistic hydrodynamics
• Active Learning Algorithm for Computational Physics
• A supervised learning algorithm for interacting topological insulators based on local curvature
• Discovering two-dimensional magnetic topological insulators by machine learning
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Distinguishing an Anderson Insulator from a Many-Body Localized phase through space-time snapshots with Neural Networks
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Unsupervised machine learning approaches to the $q$-state Potts model
• Machine Learning of Knot Topology in Non-Hermitian Band Braids
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?
• Visualizing Neural Network Developing Perturbation Theory
• Machine learning phases and criticalities without using real data for training
• Multi-faceted machine learning of competing orders in disordered interacting systems
• Engineering Topological Phases Guided by Statistical and Machine Learning Methods
• Machine learning of XY model on a spherical Fibonacci lattice
• Experimental demonstration of adversarial examples in learning topological phases
• Deep learning Local Reduced Density Matrices for Many-body Hamiltonian Estimation
• Supervised and Unsupervised Machine Learning of Structural Phases of Polymers Adsorbed to Nanowires
• Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
• Unsupervised identification of Floquet topological phase boundaries
• Observing a topological phase transition with deep neural networks from experimental images of ultracold atoms
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees
• Adversarial Machine Learning Phases of Matter
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Generative learning for the problem of critical slowing down in lattice Gross Neveu model
• Sampling U(1) gauge theory using a re-trainable conditional flow-based model
• Casimir effect with machine learning
• Cavity-Heisenberg spin-$j$ chain quantum battery and reinforcement learning optimization
• Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
• Identifying topology of leaky photonic lattices with machine learning
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Efficient and quantum-adaptive machine learning with fermion neural networks
• A simple framework for contrastive learning phases of matter
• Ground-state properties via machine learning quantum constraints
• Rapidly Encoding Generalizable Dynamics in a Euclidean Symmetric Neural Network
• Machine learning of mirror skin effects in the presence of disorder
• Predicting topological invariants and unconventional superconducting pairing from density of states and machine learning
• Discovering conservation laws from trajectories via machine learning
• Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
• Quaternion-based machine learning on topological quantum systems
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Machine learning classification of two-dimensional vortex configurations
• Effective classical correspondence of the Mott transition
• Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks
• Renormalization-group-inspired neural networks for computing topological invariants
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• Probing topological properties of 3D lattice dimer model with neural networks
• Phase classification in the long-range Harper model using machine learning
• Supervised learning of an interacting 2D hard-core boson model of a weak topological insulator using correlation functions
• Classifying topological neural network quantum states via diffusion maps
• Quantum circuit complexity and unsupervised machine learning of topological order
• Confusion-driven machine learning of structural phases of a flexible, magnetic Stockmayer polymer
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• Deep learning of topological phase transitions from entanglement aspects: An unsupervised way
• A universal neural network for learning phases and criticalities
• Machine learning topological energy braiding of non-Bloch bands
• Discovering quasiorder parameters in the Potts model: A bridge between machine learning and critical phenomena
• Randomized-gauge test for machine learning of Ising model order parameter
• Detecting the Largest Correlations using the Correlation Density Matrix: a Quantum Monte Carlo Approach
• Unsupervised Learning of Symmetry Protected Topological Phase Transitions
• Machine learning of the Ising model on a spherical Fibonacci lattice