Multi-channel convolutional neural quantum embedding

Abstract

Classification using variational quantum circuits is a promising frontier in quantum machine learning. Quantum supervised learning (QSL) applied to classical data using variational quantum circuits involves embedding the data into a quantum Hilbert space and optimizing the circuit parameters to train the measurement process. In this context, the efficacy of QSL is inherently influenced by the selection of quantum embedding. In this study, we introduce a classical-quantum hybrid approach for optimizing quantum embedding beyond the limitations of the standard circuit model of quantum computation (i.e., completely positive and trace-preserving maps) for general multi-channel data. We benchmark the performance of various models in our framework using the CIFAR-10 and Tiny ImageNet datasets and provide theoretical analyses that guide model design and optimization.

20 pages, 7 figures

References in corpus (36)

• Quantum Computing in the NISQ era and beyond
• A variational eigenvalue solver on a quantum processor
• Variational Quantum Algorithms
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum Convolutional Neural Networks
• Error mitigation for short-depth quantum circuits
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum advantage in learning from experiments
• Quantum convolutional neural network for classical data classification
• Quantum state discrimination and its applications
• Hierarchical quantum classifiers
• Average-case complexity versus approximate simulation of commuting quantum computations
• Mitigation of readout noise in near-term quantum devices by classical post-processing based on detector tomography
• Variational Quantum Linear Solver
• Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• The theory of the quantum kernel-based binary classifier
• Analysis and synthesis of feature map for kernel-based quantum classifier
• A hybrid quantum-classical approach to mitigating measurement errors
• Variational Quantum Approximate Support Vector Machine with Inference Transfer
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Quantum readout error mitigation via deep learning
• Machine Learning Applications of Quantum Computing: A Review
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• Synergetic quantum error mitigation by randomized compiling and zero-noise extrapolation for the variational quantum eigensolver
• Variational quantum state discriminator for supervised machine learning
• Sequential optimal selection of a single-qubit gate and its relation to barren plateau in parameterized quantum circuits
• Robust quantum classifier with minimal overhead
• NMR quantum information processing
• Expressivity of deterministic quantum computation with one qubit