Heuristic machinery for thermodynamic studies of SU(N) fermions with neural networks

Abstract

The power of machine learning (ML) provides the possibility of analyzing experimental measurements with an unprecedented sensitivity. However, it still remains challenging to probe the subtle effects directly related to physical observables and to understand physics behind from ordinary experimental data using ML. Here, we introduce a heuristic machinery by using machine learning analysis. We use our machinery to guide the thermodynamic studies in the density profile of ultracold fermions interacting within SU($N$) spin symmetry prepared in a quantum simulator. Although such spin symmetry should manifest itself in a many-body wavefuction, it is elusive how the momentum distribution of fermions, the most ordinary measurement, reveals the effect of spin symmetry. Using a fully trained convolutional neural network (NN) with a remarkably high accuracy of $\sim$94$\%$ for detection of the spin multiplicity, we investigate how the accuracy depends on various less-pronounced effects with filtered experimental images. Guided by our machinery, we directly measure a thermodynamic compressibility from density fluctuations within the single image. Our machine learning framework shows a potential to validate theoretical descriptions of SU($N$) Fermi liquids, and to identify less-pronounced effects even for highly complex quantum matter with minimal prior understanding.

arXiv comment11 pages, 5 figures, 1 table

References in corpus (37)

• The electronic properties of graphene
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Two-orbital SU(N) magnetism with ultracold alkaline-earth atoms
• Large momentum part of fermions with large scattering length
• Energetics of a strongly correlated Fermi gas
• A one-dimensional liquid of fermions with tunable spin
• Generalized Virial Theorem and Pressure Relation for a strongly correlated Fermi gas
• Molecular Probe of Pairing in the BEC-BCS Crossover
• Spectroscopic observation of SU(N)-symmetric interactions in Sr orbital magnetism
• Observation of two-orbital spin-exchange interactions with ultracold SU(N)-symmetric fermions
• An SU(N) Mott insulator of an atomic Fermi gas realized by large-spin Pomeranchuk cooling
• Ultracold Fermi Gases with Emergent SU(N) Symmetry
• Ultracold Gases of Ytterbium: Ferromagnetism and Mott States in an SU(6) Fermi System
• Verification of universal relations in a strongly interacting Fermi gas
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Universal behavior of pair correlations in a strongly interacting Fermi gas
• Direct observation of coherent inter-orbital spin-exchange dynamics
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Two and Three-body Contacts in the Unitary Bose Gas
• Suppression of Density Fluctuations in a Quantum Degenerate Fermi Gas
• Antiferromagnetic spin correlation of SU($\mathcal{N}$) Fermi gas in an optical super-lattice
• Emergence of multi-body interactions in few-atom sites of a fermionic lattice clock
• Evidence for universal relations describing a gas with $p$-wave interactions
• Spin-orbit coupled two-electron Fermi gases of ytterbium atoms
• Universal Properties of a Strongly Interacting Fermi Gas at a $p$-wave Resonance
• Thermodynamics of a deeply degenerate SU($N$)-symmetric Fermi gas
• Connecting few-body inelastic decay to many-body correlations: a weakly coupled impurity in a resonant Fermi gas
• Ideal Gases in Time-Dependent Traps
• Interaction Control of Ultracold Alkaline-Earth Atoms
• Thermalization and Sub-Poissonian Density Fluctuations in a Degenerate Molecular Fermi Gas
• Complex correlations in high harmonic generation of matter-wave jets revealed by pattern recognition
• Theory of SU(N) Fermi liquid
• Collisions in zero temperature Fermi gases
• Collective excitations in two-dimensional SU($N$) Fermi gases with tunable spin
• Effective statistical fringe removal algorithm for high-sensitivity imaging of ultracold atoms