Quantum convolutional neural network for classical data classification

Abstract

With the rapid advance of quantum machine learning, several proposals for the quantum-analogue of convolutional neural network (CNN) have emerged. In this work, we benchmark fully parameterized quantum convolutional neural networks (QCNNs) for classical data classification. In particular, we propose a quantum neural network model inspired by CNN that only uses two-qubit interactions throughout the entire algorithm. We investigate the performance of various QCNN models differentiated by structures of parameterized quantum circuits, quantum data encoding methods, classical data pre-processing methods, cost functions and optimizers on MNIST and Fashion MNIST datasets. In most instances, QCNN achieved excellent classification accuracy despite having a small number of free parameters. The QCNN models performed noticeably better than CNN models under the similar training conditions. Since the QCNN algorithm presented in this work utilizes fully parameterized and shallow-depth quantum circuits, it is suitable for Noisy Intermediate-Scale Quantum (NISQ) devices.

18 pages, 7 figures

References in corpus (4)

• Quantum random access memory
• Quantum Computation of Electronic Transitions using a Variational Quantum Eigensolver
• Circuit-Based Quantum Random Access Memory for Classical Data
• Circuit-based quantum random access memory for classical data with continuous amplitudes

Cited by in corpus (56)

• Quantum machine learning for image classification
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Recent advances for quantum classifiers
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Does provable absence of barren plateaus imply classical simulability?
• Classical-to-quantum convolutional neural network transfer learning
• Linear-depth quantum circuits for multiqubit controlled gates
• Quantum Convolutional Neural Networks for Multi-Channel Supervised Learning
• Variational quantum one-class classifier
• Hierarchical quantum circuit representations for neural architecture search
• Quantum Convolutional Neural Networks with Interaction Layers for Classification of Classical Data
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• Harnessing Quantum Extreme Learning Machines for image classification
• Compact quantum kernel-based binary classifier
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity
• Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images
• What can we learn from quantum convolutional neural networks?
• Randomness-enhanced expressivity of quantum neural networks
• Variational quantum state discriminator for supervised machine learning
• Non-Unitary Quantum Machine Learning
• The role of data embedding in equivariant quantum convolutional neural networks
• Opportunities and challenges of quantum computing for climate modelling
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Hybrid quantum learning with data re-uploading on a small-scale superconducting quantum simulator
• Pulsar Classification: Comparing Quantum Convolutional Neural Networks and Quantum Support Vector Machines
• Quantum autoencoders for image classification
• Quantum support vector data description for anomaly detection
• Assessing the Impact of Noise on Quantum Neural Networks: An Experimental Analysis
• Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers
• Digital-analog quantum convolutional neural networks for image classification
• Distributed quantum machine learning via classical communication
• SLIQ: Quantum Image Similarity Networks on Noisy Quantum Computers
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Distributed Partial Quantum Consensus of Qubit Networks with Connected Topologies
• A Post-Training Approach for Mitigating Overfitting in Quantum Convolutional Neural Networks
• Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
• QDCNN: Quantum Dilated Convolutional Neural Network
• Supervised Learning Guarantee for Quantum AdaBoost
• QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networks
• Quantum Inception Score
• Image Classification by Throwing Quantum Kitchen Sinks at Tensor Networks
• Backpropagation scaling in parameterised quantum circuits
• Permutation-equivariant quantum convolutional neural networks
• Tristochastic operations and convolutions of quantum states
• ResQuNNs: Towards Enabling Deep Learning in Quantum Convolution Neural Networks
• Expressivity of deterministic quantum computation with one qubit
• Quantum convolutional channels and multiparameter families of 2-unitary matrices
• A quantum tug of war between randomness and symmetries on homogeneous spaces
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Multi-channel convolutional neural quantum embedding
• A variational quantum algorithm for entanglement quantification
• Identification of quantum generative circuits with parallel quantum neural network
• Vortex Detection from Quantum Data
• FRQI Pairs method for image classification using Quantum Recurrent Neural Network