Interpreting machine learning of topological quantum phase transitions

2019/12/31 by Yi Zhang, Paul Ginsparg, Eun-Ah Kim
Materials Science · Physics and Astronomy · #Artificial neural network #Feature (linguistics) #Feature selection #Interpretability #Machine Learning in Materials Science #Quantum #Quantum computer #Quantum many-body systems #Spin (aerodynamics) #Stability (learning theory) #Topological Materials and Phenomena #Topology (electrical circuits) #cond-mat.dis-nn #cond-mat.str-el #physics.comp-ph

paper · pdf · doi:10.1103/physrevresearch.2.023283

published as Phys. Rev. Research 2, 023283 (2020) · 9 pages, 11 figures

openalex created_date 2019/12/26 · openalex publication_date 2020/06/04 · arxiv created 2020/12/07 · arxiv updated 2020/12/08 · openalex updated_date 2026/08/05

Abstract

The authors tackle the issue of interpretability in machine learning topological quantum phases in models of Chern insulator, ℤ₂ topological insulator, and ℤ₂ quantum spin liquid. The authors use artificial neural network aided by physical insight underlying the feature selection through quantum loop topography to understand the artificial neural network's decision-making criteria in each of the three cases

Citations

• Proper Definition of Spin Current in Spin-Orbit Coupled Systems
• Z2Topological Order and the Quantum Spin Hall Effect
• Approximation by superpositions of a sigmoidal function
• Anyons in an exactly solved model and beyond
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning quantum phases of matter beyond the fermion sign problem
• Machine learning action parameters in lattice quantum chromodynamics
• Deep learning topological invariants of band insulators
• Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal