Hybrid Quantum-Classical Convolutional Neural Networks

Abstract

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN.

8 pages, 4 figures

References in corpus (32)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Convolutional Sequence to Sequence Learning
• Supervised learning with quantum enhanced feature spaces
• The theory of variational hybrid quantum-classical algorithms
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Quantum principal component analysis
• Language Modeling with Gated Convolutional Networks
• Quantum Computational Supremacy
• Quantum generative adversarial learning
• Quantum generative adversarial networks
• Continuous-variable quantum neural networks
• Superconducting Quantum Computing: A Review
• IBM Q Experience as a versatile experimental testbed for simulating open quantum systems
• The Expressive Power of Parameterized Quantum Circuits
• Demonstration of Shor's quantum factoring algorithm using photonic qubits
• Quantum generative adversarial learning in a superconducting quantum circuit
• Experimental Blind Quantum Computing for a Classical Client
• General-purpose quantum circuit simulator with Projected Entangled-Pair States and the quantum supremacy frontier
• Quantum Algorithms for Deep Convolutional Neural Networks
• Variational Quantum Circuits for Quantum State Tomography
• Noise-Resilient Variational Hybrid Quantum-Classical Optimization
• Simulating the Sycamore quantum supremacy circuits
• Demonstration of Topological Data Analysis on a Quantum Processor
• Expressibility and trainability of parameterized analog quantum systems for machine learning applications
• Verifying Random Quantum Circuits with Arbitrary Geometry Using Tensor Network States Algorithm
• A scheme for automatic differentiation of complex loss functions

Cited by in corpus (44)

• Strong quantum computational advantage using a superconducting quantum processor
• Quantum convolutional neural network for classical data classification
• Superconducting Quantum Computing: A Review
• Realization of an Error-Correcting Surface Code with Superconducting Qubits
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Quantum-Inspired Support Vector Machine
• Quantum machine learning for image classification
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Recent advances for quantum classifiers
• Quantum Neural Network Classifiers: A Tutorial
• RGB Image Classification with Quantum Convolutional Ansaetze
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Variational quantum process tomography
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• Quantum Capsule Networks
• Quantifying Unknown Quantum Entanglement via a Hybrid Quantum-Classical Machine Learning Framework
• Let Quantum Neural Networks Choose Their Own Frequencies
• Quantum Convolutional Neural Networks with Interaction Layers for Classification of Classical Data
• A duplication-free quantum neural network for universal approximation
• A biological sequence comparison algorithm using quantum computers
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• The quantum cost function concentration dependency on the parametrization expressivity
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Quantum gradient descent algorithms for nonequilibrium steady states and linear algebraic systems
• Embedding Learning in Hybrid Quantum-Classical Neural Networks
• Noise-Resistant Quantum State Compression Readout
• Evolution strategies: Application in hybrid quantum-classical neural networks
• Non-Unitary Quantum Machine Learning
• Evaluating the Resilience of Variational Quantum Algorithms to Leakage Noise
• Quantum algorithms for group convolution, cross-correlation, and equivariant transformations
• Quantum Generative Adversarial Networks in a Silicon Photonic Chip with Maximum Expressibility
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Parameter-Parallel Distributed Variational Quantum Algorithm
• Distributed Partial Quantum Consensus of Qubit Networks with Connected Topologies
• QDCNN: Quantum Dilated Convolutional Neural Network
• Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
• Restricting to the chip architecture maintains the quantum neural network accuracy
• Quantum Adjoint Convolutional Layers for Effective Data Representation
• Lean classical-quantum hybrid neural network model for image classification
• Application of Quantum Pre-Processing Filter for Binary Image Classification with Small Samples
• Barren plateaus are amplified by the dimension of qudits
• Quantum Sparse Coding and Decoding Based on Quantum Network
• LArTPC hit-based topology classification with quantum machine learning and symmetry