Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning

Abstract

Single-shot images are the standard readout of experiments with ultracold atoms -- the tarnished looking glass into their many-body physics. The efficient extraction of observables from single-shot images is thus crucial. Here, we demonstrate how artificial neural networks can optimize this extraction. In contrast to standard averaging approaches, machine learning allows both one- and two-particle densities to be accurately obtained from a drastically reduced number of single-shot images. Quantum fluctuations and correlations are directly harnessed to obtain physical observables for bosons in a tilted double-well potential at an unprecedented accuracy. Strikingly, machine learning also enables a reliable extraction of momentum-space observables from real-space single-shot images and vice versa. This obviates the need for a reconfiguration of the experimental setup between in-situ and time-of-flight imaging, thus potentially granting an outstanding reduction in resources.

arXiv comment7+8 pages, 3+8 figures, software available at http://ultracold.org

References in corpus (92)

• Many-Body Physics with Ultracold Gases
• Quantum Simulation
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Ultracold atomic gases in optical lattices: mimicking condensed matter physics and beyond
• Direct Observation of Tunneling and Nonlinear Self-Trapping in a single Bosonic Josephson Junction
• A quantum gas microscope - detecting single atoms in a Hubbard regime optical lattice
• Machine learning phases of matter
• Single-Atom Resolved Fluorescence Imaging of an Atomic Mott Insulator
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Experimental Observation of a Generalized Gibbs Ensemble
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Tools for quantum simulation with ultracold atoms in optical lattices
• Quantum Entanglement in Neural Network States
• Machine learning quantum phases of matter beyond the fermion sign problem
• The multi-configurational time-dependent Hartree method for bosons: Many-body dynamics of bosonic systems
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Reconstructing quantum states with generative models
• Machine Learning Topological States
• On solving quantum many-body problems by experiment
• Quantum Loop Topography for Machine Learning
• Two Fermions in a double well: Exploring a fundamental building block of the Hubbard model
• Single Particle Tunneling in Strongly Driven Double Well Potentials
• Learning Thermodynamics with Boltzmann Machines
• Machine Learning Phases of Strongly Correlated Fermions
• Symmetries and many-body excited states with neural-network quantum states
• Equivalence of restricted Boltzmann machines and tensor network states
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Role of excited states in the splitting dynamics of interacting Bose-Einstein condensates when ramping-up a barrier
• Observation of Quantized Conductance in Neutral Matter
• Approximating quantum many-body wave-functions using artificial neural networks
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Quantum Entanglement in Deep Learning Architectures
• Spatial fragmentation of a Bose-Einstein condensate in a double-well potential
• Twin-atom beams
• Exact quantum dynamics of a bosonic Josephson junction
• Unsupervised machine learning and band topology
• Multiconfigurational time-dependent Hartree approaches for indistinguishable particles
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Reduced density matrices and coherence of trapped interacting bosons
• Constructing exact representations of quantum many-body systems with deep neural networks
• Probing many-body localization with neural networks
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• The Multi-Layer Multi-Configuration Time-Dependent Hartree Method for Bosons: Theory, Implementation and Applications
• Time-dependent restricted-active-space self-consistent field theory for laser-driven many-electron dynamics
• A unified ab-initio approach to the correlated quantum dynamics of ultracold fermionic and bosonic mixtures
• Relaxation to a Phase-locked Equilibrium State in a One-dimensional Bosonic Josephson Junction
• Single-particle-sensitive imaging of freely propagating ultracold atoms
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• The multiconfigurational time-dependent Hartree for fermions: Implementation, exactness and application to few-fermion tunneling to open space
• The multiconfigurational time-dependent Hartree method for bosons with internal degrees of freedom: Theory and composite fragmentation of multi-component Bose-Einstein condensates
• Experimental Characterization of Two-Particle Entanglement through Position and Momentum Correlations
• Out of equilibrium dynamics with Matrix Product States
• Chiral Topological Phases from Artificial Neural Networks
• Fragmented Superradiance of a Bose-Einstein Condensate in an Optical Cavity
• Neural network quantum state tomography in a two-qubit experiment
• Parametric Excitation of a Bose-Einstein Condensate: From Faraday Waves to Granulation
• Quantized conductance through a dissipative atomic point contact
• Single shot simulations of dynamic quantum many-body systems
• MCTDH-X: The multiconfigurational time-dependent Hartree method for indistinguishable particles software
• Precise measurement of quantum observables with neural-network estimators
• Images of the Dark Soliton in a Depleted Condensate
• Negative quench induced excitation dynamics for ultracold bosons in one-dimensional lattices
• Open source Matrix Product States: Opening ways to simulate entangled many-body quantum systems in one dimension
• Controlling the Floquet state population and observing micromotion in a periodically driven two-body quantum system
• Absorption Imaging of Ultracold Atoms on Atom Chips
• Transfer learning for scalability of neural-network quantum states
• Universality of Fragmentation in the Schrödinger Dynamics of Bosonic Josephson Junctions
• Principal Component Analysis for Fermionic Critical Points
• Order parameter and detection for crystallized dipolar bosons in lattices
• Interaction Quench Induced Multimode Dynamics of Finite Atomic Ensembles
• The Tensor Network Theory Library
• Time-dependent restricted-active-space self-consistent-field theory for bosonic many-body systems
• Mode coupling of interaction quenched ultracold few-boson ensembles in periodically driven lattices
• Recursive formulation of the multiconfigurational time-dependent Hartree method for fermions, bosons and mixtures thereof in terms of one-body density operators
• Experimental extraction of the quantum effective action for a non-equilibrium many-body system
• Extracting Critical Exponent by Finite-Size Scaling with Convolutional Neural Networks
• Single-exposure absorption imaging of ultracold atoms using deep learning
• Interpretable and unsupervised phase classification
• Multispecies time-dependent restricted-active-space self-consistent-field theory for ultracold atomic and molecular gases
• Detecting One-Dimensional Dipolar Bosonic Crystal Orders via Full Distribution Functions
• Quantum dynamical response of ultracold few boson ensembles in finite optical lattices to multiple interaction quenches
• Identifying Product Order with Restricted Boltzmann Machines
• Vortex nucleation in mesoscopic Bose superfluid and breaking of the parity symmetry
• Single shot imaging of trapped Fermi gas
• On the observability of Pauli crystals
• Management of the Correlations of Ultracold Bosons in Triple Wells
• Number fluctuations of cold spatially split bosonic objects