What can we learn from quantum convolutional neural networks?

Abstract

Quantum machine learning (QML) shows promise for analyzing quantum data. A notable example is the use of quantum convolutional neural networks (QCNNs), implemented as specific types of quantum circuits, to recognize phases of matter. In this approach, ground states of many-body Hamiltonians are prepared to form a quantum dataset and classified in a supervised manner using only a few labeled examples. However, this type of dataset and model differs fundamentally from typical QML paradigms based on feature maps and parameterized circuits. In this study, we demonstrate how models utilizing quantum data can be interpreted through hidden feature maps, where physical features are implicitly embedded via ground-state feature maps. By analyzing selected examples previously explored with QCNNs, we show that high performance in quantum phase recognition comes from generating a highly effective basis set with sharp features at critical points. The learning process adapts the measurement to create sharp decision boundaries. Our analysis highlights improved generalization when working with quantum data, particularly in the limited-shots regime. Furthermore, translating these insights into the domain of quantum scientific machine learning, we demonstrate that ground-state feature maps can be applied to fluid dynamics problems, expressing shock wave solutions with good generalization and proven trainability.

15 pages, 9 figures

References in corpus (66)

• Quantum Machine Learning
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum computational chemistry
• Quantum Circuit Learning
• Adiabatic Quantum Computing
• Quantum Convolutional Neural Networks
• An introduction to quantum machine learning
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• Quantum algorithms: an overview
• Circuit-centric quantum classifiers
• Quantum Phases of Matter on a 256-Atom Programmable Quantum Simulator
• Zoo of quantum-topological phases of matter
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Determining eigenstates and thermal states on a quantum computer using quantum imaginary time evolution
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Quantum Data Fitting
• Simulating Lattice Gauge Theories within Quantum Technologies
• Generalization in quantum machine learning from few training data
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Quantum-enhanced machine learning
• Transfer learning in hybrid classical-quantum neural networks
• Quantum convolutional neural network for classical data classification
• Quantum Computing for Finance: State of the Art and Future Prospects
• Digital quantum simulation of fermionic models with a superconducting circuit
• Hierarchical quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• Active learning machine learns to create new quantum experiments
• Quantum computing for finance
• Differentiable Learning of Quantum Circuit Born Machine
• Prediction by linear regression on a quantum computer
• Information-theoretic bounds on quantum advantage in machine learning
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Exploring entanglement and optimization within the Hamiltonian Variational Ansatz
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Is quantum advantage the right goal for quantum machine learning?
• Solving nonlinear differential equations with differentiable quantum circuits
• Exploiting symmetry in variational quantum machine learning
• Experimental quantum speed-up in reinforcement learning agents
• Theory of overparametrization in quantum neural networks
• Group-Invariant Quantum Machine Learning
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Entanglement Devised Barren Plateau Mitigation
• Quantum Algorithm for Linear Regression
• Efficient variational simulation of non-trivial quantum states
• A resource efficient approach for quantum and classical simulations of gauge theories in particle physics
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Observing ground-state properties of the Fermi-Hubbard model using a scalable algorithm on a quantum computer
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• Understanding quantum machine learning also requires rethinking generalization
• On the energy landscape of symmetric quantum signal processing
• Pivot Hamiltonians as generators of symmetry and entanglement
• Quantum Kernel Methods for Solving Differential Equations
• Higgs analysis with quantum classifiers
• Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
• Hamiltonian operator approximation for energy measurement and ground state preparation
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Introducing Non-Linear Activations into Quantum Generative Models

Cited by in corpus (4)

• Does provable absence of barren plateaus imply classical simulability?
• Ground state-based quantum feature maps
• Vortex Detection from Quantum Data
• Learning complexity gradually in quantum machine learning models