Unsupervised Manifold Clustering of Topological Phononics

Abstract

Classification of topological phononics is challenging due to the lack of universal topological invariants and the randomness of structure patterns. Here, we show the unsupervised manifold learning for clustering topological phononics without any priori knowledge, neither topological invariants nor supervised trainings, even when systems are imperfect or disordered. This is achieved by exploiting the real-space projection operator about finite phononic lattices to describe the correlation between oscillators. We exemplify the efficient unsupervised manifold clustering in typical phononic systems, including one-dimensional Su-Schrieffer-Heeger-type phononic chain with random couplings, amorphous phononic topological insulators, higher-order phononic topological states and non-Hermitian phononic chain with random dissipations. The results would inspire more efforts on applications of unsupervised machine learning for topological phononic devices and beyond.

arXiv comment6 pages, 4 figures

References in corpus (58)

• Topological Insulators
• Berry Phase Effects on Electronic Properties
• Anyons in an exactly solved model and beyond
• Maximally localized Wannier functions: Theory and applications
• Making Sense of Non-Hermitian Hamiltonians
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Edge states and topological invariants of non-Hermitian systems
• Quantized Electric Multipole Insulators
• Colloquium: Topological Band Theory
• Topological phases of non-Hermitian systems
• Machine learning phases of matter
• Biorthogonal Bulk-Boundary Correspondence in Non-Hermitian Systems
• Acoustic topological insulator and robust one-way sound transport
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Training deep neural networks for the inverse design of nanophotonic structures
• Topological Band Theory for Non-Hermitian Hamiltonians
• Anomalous edge state in a non-Hermitian lattice
• Observation of phononic helical edge states in a mechanical 'topological insulator'
• Observation of a phononic quadrupole topological insulator
• A Generative Model for Inverse Design of Metamaterials
• Observation of topological valley transport of sound in sonic crystals
• A high-bias, low-variance introduction to Machine Learning for physicists
• Acoustic higher-order topological insulator on a Kagome lattice
• Topological Phononic Crystals with One-Way Elastic Edge Waves
• Non-Hermitian robust edge states in one-dimension: Anomalous localization and eigenspace condensation at exceptional points
• Topologically protected elastic waves in phononic metamaterials
• Edge Modes, Degeneracies, and Topological Numbers in Non-Hermitian Systems
• Learning phase transitions by confusion
• Probing topological invariants in the bulk of a non-Hermitian optical system
• Discovering Phase Transitions with Unsupervised Learning
• Topology by Dissipation in Atomic Quantum Wires
• Designer disordered materials with large complete photonic band gaps
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Second-Order Topological Phases in Non-Hermitian Systems
• Observation of second-order topological insulators in sonic crystals
• Wannier representation of Z_2 topological insulators
• Topological negative refraction of surface acoustic waves in a Weyl phononic crystal
• Synthetic gauge fields and Weyl point in Time-Reversal Invariant Acoustic Systems
• The emergence, coalescence and topological properties of multiple exceptional points and their experimental realization
• New topological invariants in non-Hermitian systems
• Topological Nature of the Phonon Hall Effect
• Amorphous topological insulators constructed from random point sets
• Mapping topological order in coordinate space
• Classification of topological phonons in linear mechanical metamaterials
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Topological Insulators in Random Lattices
• Designing Perturbative Metamaterials from Discrete Models: From Veselago lenses to topological insulators
• Noise bridges dynamical correlation and topology in coupled oscillator networks
• Dimensional hierarchy of higher-order topology in three-dimensional sonic crystals
• Pseudospins and topological effects of phonons in a Kekule lattice
• Machine learning out-of-equilibrium phases of matter
• Experimental demonstration of an anisotropic exceptional point
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Berry Phase and Topological Effects of Phonons
• Topological localization in out-of-equilibrium dissipative systems

Cited by in corpus (35)

• Unsupervised machine learning and band topology
• Controlling mass and energy diffusion with metamaterials
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Unsupervised machine learning of topological phase transitions from experimental data
• Measurement-induced criticality as a data-structure transition
• Topological thermal transport
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Phononic real Chern insulator with protected corner modes in graphynes
• Unsupervised Learning of Non-Hermitian Topological Phases
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Machine learning topological invariants of non-Hermitian systems
• Topological Persistence Machine of Phase Transitions
• Topological data analysis and machine learning
• Coexistence of zero-, one- and two-dimensional degeneracy in tetragonal SnO${}_2$ phonons
• Intrinsic dimension of path integrals: data mining quantum criticality and emergent simplicity
• Generative models for sampling and phase transition indication in spin systems
• Topological effects of phonons in GaN and AlxGa1-xN: A potential perspective for tuning phonon transport
• Interpretable and unsupervised phase classification
• Visualizing Quantum Phases And Identifying Quantum Phase Transitions By Nonlinear Dimensionality Reduction
• Directional Design of Materials Based on the Multi-Objective Optimization: A Case Study of Two-Dimensional Thermoelectric SnSe
• Unsupervised Learning of Topological Non-Abelian Braiding in Non-Hermitian Bands
• Constrained tandem neural network assisted inverse design of metasurfaces for microwave absorption
• Unsupervised learning of topological phase diagram using topological data analysis
• Machine Learning of Knot Topology in Non-Hermitian Band Braids
• Quantum diffusion map for nonlinear dimensionality reduction
• Machine learning for percolation utilizing auxiliary Ising variables
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• Experimental demonstration of adversarial examples in learning topological phases
• Unsupervised identification of Floquet topological phase boundaries
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees
• Adversarial Machine Learning Phases of Matter
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Classifying topological neural network quantum states via diffusion maps
• Quantum circuit complexity and unsupervised machine learning of topological order