Machine Learning Topological Phases with a Solid-state Quantum Simulator

Abstract

We report an experimental demonstration of a machine learning approach to identify exotic topological phases, with a focus on the three-dimensional chiral topological insulators. We show that the convolutional neural networks---a class of deep feed-forward artificial neural networks with widespread applications in machine learning---can be trained to successfully identify different topological phases protected by chiral symmetry from experimental raw data generated with a solid-state quantum simulator. Our results explicitly showcase the exceptional power of machine learning in the experimental detection of topological phases, which paves a way to study rich topological phenomena with the machine learning toolbox.

Main text: 5 pages with 3 figures; supplemental materials: 8 pages with 4 figures and 2 tables; accepted at Physical Review Letters

References in corpus (11)

• A topological Dirac insulator in a quantum spin Hall phase : Experimental observation of first strong topological insulator
• Classification of topological insulators and superconductors in three spatial dimensions
• Topological Field Theory of Time-Reversal Invariant Insulators
• Learning phase transitions by confusion
• Bloch vectors for qudits
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Observation of topological transitions in interacting quantum circuits
• Fractional topological insulators in three dimensions
• Direct Probe of Topological Order for Cold Atoms
• Electromagnetic and thermal responses of Z topological insulators and superconductors in odd spatial dimensions
• Quantized electromagnetic response of three-dimensional chiral topological insulators