Machine prediction of topological transitions in photonic crystals
arXiv:1907.07996 · doi:10.1103/PhysRevApplied.14.044032
Abstract
We train artificial neural networks to distinguish the geometric phases of a set of bands in 1D photonic crystals. We find that the trained network yields remarkably accurate predictions of the topological phases for 1D photonic crystals, even for the geometric and material parameters that are outside of the range of the trained dataset. Another remarkable capability of the trained network is to predict the boundary of topological transition in the parameter space, where a large portion of trained data in the vicinity of that boundary is excluded purposely. The results indicate that the network indeed learns the very essence of the structure of Maxwell's equations, and has the ability of predicting the topological invariants beyond the range of the training dataset.
arXiv comment11 pages, 5 figures
References in corpus (15)
- Deep Learning with Coherent Nanophotonic Circuits
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Training deep neural networks for the inverse design of nanophotonic structures
- A Generative Model for Inverse Design of Metamaterials
- A high-bias, low-variance introduction to Machine Learning for physicists
- Learning phase transitions by confusion
- Surface Impedance and Bulk Band Geometric Phases in One-Dimensional Systems
- Quantum Entanglement in Neural Network States
- Machine Learning Topological States
- Quantum Loop Topography for Machine Learning
- Machine Learning Topological Invariants with Neural Networks
- Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
- Deep Learning Topological Invariants of Band Insulators
- Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
- Emergent Quantum Mechanics in an Introspective Machine Learning Architecture