Efficient and quantum-adaptive machine learning with fermion neural networks

Abstract

Classical artificial neural networks have witnessed widespread successes in machine-learning applications. Here, we propose fermion neural networks (FNNs) whose physical properties, such as local density of states or conditional conductance, serve as outputs, once the inputs are incorporated as an initial layer. Comparable to back-propagation, we establish an efficient optimization, which entitles FNNs to competitive performance on challenging machine-learning benchmarks. FNNs also directly apply to quantum systems, including hard ones with interactions, and offer in-situ analysis without preprocessing or presumption. Following machine learning, FNNs precisely determine topological phases and emergent charge orders. Their quantum nature also brings various advantages: quantum correlation entitles more general network connectivity and insight into the vanishing gradient problem, quantum entanglement opens up novel avenues for interpretable machine learning, etc.

arXiv comment18 pages, 12 figures

References in corpus (74)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• Anyons in an exactly solved model and beyond
• Quantum Machine Learning
• Variational Quantum Algorithms
• Quantum Simulation
• Area laws for the entanglement entropy - a review
• Quantum information with Rydberg atoms
• Spins in few-electron quantum dots
• Machine learning and the physical sciences
• Quantum computational advantage using photons
• Barren plateaus in quantum neural network training landscapes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Exceptional Topology of Non-Hermitian Systems
• Non-Hermitian Physics
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Strong quantum computational advantage using a superconducting quantum processor
• Many-Body Physics with Individually-Controlled Rydberg Atoms
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Calculation of reduced density matrices from correlation functions
• Evaluating analytic gradients on quantum hardware
• The power of quantum neural networks
• A Rydberg Quantum Simulator
• Quantum Computational Supremacy
• Many-body quantum state tomography with neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Learning phase transitions by confusion
• Reduced density matrices and entanglement entropy in free lattice models
• Programmable quantum simulation of 2D antiferromagnets with hundreds of Rydberg atoms
• Challenges and Opportunities in Quantum Machine Learning
• Generation and manipulation of Schrödinger cat states in Rydberg atom arrays
• On the quantum, classical and total amount of correlations in a quantum state
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Nonlocal Dynamical Correlations of Strongly Interacting Electron Systems
• Quantum Optimization of Maximum Independent Set using Rydberg Atom Arrays
• Training variational quantum algorithms is NP-hard
• Quantum advantage with shallow circuits
• Controlling many-body dynamics with driven quantum scars in Rydberg atom arrays
• Quantum simulation of a Fermi-Hubbard model using a semiconductor quantum dot array
• Exact solution of the Falicov-Kimball model with dynamical mean-field theory
• Active learning machine learns to create new quantum experiments
• Machine Learning Topological States
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Information-theoretic bounds on quantum advantage in machine learning
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Provably efficient machine learning for quantum many-body problems
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• On the von Neumann capacity of noisy quantum channels
• Deviations from Fermi-liquid behavior above $T_c$ in 2D short coherence length superconductors
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Long-range coherent coupling in a quantum dot array
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Quantum simulation of Fermi-Hubbard models in semiconductor quantum dot arrays
• Topological Quantum Compiling with Reinforcement Learning
• Artificial Neural Network Approach to the Analytic Continuation Problem
• Fermionic quantum processing with programmable neutral atom arrays
• Thermodynamics of the two-dimensional Falicov-Kimball model: a classical Monte Carlo study
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Quantum nonlinear optics based on two-dimensional Rydberg atom arrays
• Quantum simulation of antiferromagnetic Heisenberg chain with gate-defined quantum dots
• Interpreting machine learning of topological quantum phase transitions
• Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions
• Rapid Exploration of Topological Band Structures using Deep Learning
• Quantum Dropout: On and Over the Hardness of Quantum Approximate Optimization Algorithm
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Ground-state properties via machine learning quantum constraints

Cited by in corpus (1)

• Superior resilience to poisoning and amenability to unlearning in quantum machine learning