Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data

Abstract

Machine learning models are a powerful theoretical tool for analyzing data from quantum simulators, in which results of experiments are sets of snapshots of many-body states. Recently, they have been successfully applied to distinguish between snapshots that can not be identified using traditional one and two point correlation functions. Thus far, the complexity of these models has inhibited new physical insights from this approach. Here, using a novel set of nonlinearities we develop a network architecture that discovers features in the data which are directly interpretable in terms of physical observables. In particular, our network can be understood as uncovering high-order correlators which significantly differ between the data studied. We demonstrate this new architecture on sets of simulated snapshots produced by two candidate theories approximating the doped Fermi-Hubbard model, which is realized in state-of-the art quantum gas microscopy experiments. From the trained networks, we uncover that the key distinguishing features are fourth-order spin-charge correlators, providing a means to compare experimental data to theoretical predictions. Our approach lends itself well to the construction of simple, end-to-end interpretable architectures and is applicable to arbitrary lattice data, thus paving the way for new physical insights from machine learning studies of experimental as well as numerical data.

arXiv comment7 pages, 4 figures + 13 pages of supplemental material

References in corpus (30)

• Probing many-body dynamics on a 51-atom quantum simulator
• A quantum gas microscope - detecting single atoms in a Hubbard regime optical lattice
• Single-Atom Resolved Fluorescence Imaging of an Atomic Mott Insulator
• Experimental realization of a long-range antiferromagnet in the Hubbard model with ultracold atoms
• Realizing quantum Ising models in tunable two-dimensional arrays of single Rydberg atoms
• Theory of Underdoped Cuprates
• Direct observation of dynamical quantum phase transitions in an interacting many-body system
• Bad metallic transport in a cold atom Fermi-Hubbard system
• Machine Learning Topological Invariants with Neural Networks
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Imaging magnetic polarons in the doped Fermi-Hubbard model
• String patterns in the doped Hubbard model
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Doublon-hole correlations and fluctuation thermometry in a Fermi-Hubbard gas
• Robust Bilayer Charge-Pumping for Spin- and Density-Resolved Quantum Gas Microscopy
• Direct observation of incommensurate magnetism in Hubbard chains
• Probing hidden spin order with interpretable machine learning
• Stripes, Antiferromagnetism, and the Pseudogap in the Doped Hubbard Model at Finite Temperature
• Microscopic spinon-chargon theory of magnetic polarons in the t-J model
• Learning multiple order parameters with interpretable machines
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• One-Component Order Parameter in URu${}_2$Si${}_2$ Uncovered by Resonant Ultrasound Spectroscopy and Machine Learning
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Single-exposure absorption imaging of ultracold atoms using deep learning
• Quantum Many-Body Simulations of the 2D Fermi-Hubbard Model in Ultracold Optical Lattices
• Supervised machine learning of ultracold atoms with speckle disorder
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning

Cited by in corpus (24)

• Exploration of doped quantum magnets with ultracold atoms
• Unsupervised machine learning of topological phase transitions from experimental data
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Analyzing non-equilibrium quantum states through snapshots with artificial neural networks
• Snapshot based characterization of particle currents and the Hall response in synthetic flux lattices
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Transformer neural networks and quantum simulators: a hybrid approach for simulating strongly correlated systems
• Learning minimal representations of stochastic processes with variational autoencoders
• Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene
• Data-driven discovery of statistically relevant information in quantum simulators
• Observing a topological phase transition with deep neural networks from experimental images of ultracold atoms
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Machine learning reveals features of spinon Fermi surface
• Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
• Extracting Off-Diagonal Order from Diagonal Basis Measurements
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Unsupervised Machine Learning Phase Classification for Falicov-Kimball Model
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Attention to Quantum Complexity
• Reveal flocking phase transition of self-propelled active particles by machine learning regression uncertainty
• Artificial intelligence for representing and characterizing quantum systems
• Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders
• Neural quantum states for entanglement depth certification from randomized Pauli measurements