Transfer learning in hybrid classical-quantum neural networks

Abstract

We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.

arXiv commentAccepted in Quantum. Code available at: https://github.com/XanaduAI/quantum-transfer-learning

References in corpus (30)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• 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
• Gaussian Quantum Information
• How transferable are features in deep neural networks?
• The theory of variational hybrid quantum-classical algorithms
• Quantum machine learning in feature Hilbert spaces
• An introduction to quantum machine learning
• Circuit-centric quantum classifiers
• An Analysis of Deep Neural Network Models for Practical Applications
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Quantum Computational Supremacy
• Quantum-enhanced machine learning
• Continuous-variable quantum neural networks
• Strawberry Fields: A Software Platform for Photonic Quantum Computing
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Machine Learning Phases of Strongly Correlated Fermions
• Concrete Categorical Model of a Quantum Circuit Description Language with Measurement
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Learning to learn with quantum neural networks via classical neural networks
• Supervised learning with a quantum classifier using a multi-level system
• Transfer learning for scalability of neural-network quantum states
• Convolution filter embedded quantum gate autoencoder

Cited by in corpus (61)

• Robust data encodings for quantum classifiers
• General parameter-shift rules for quantum gradients
• Quantum Machine Learning for Chemistry and Physics
• Quantum computing models for artificial neural networks
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
• Classical-to-quantum convolutional neural network transfer learning
• Hybrid Classical-Quantum Autoencoder for Anomaly Detection
• Quantum Embedding Search for Quantum Machine Learning
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Variational learning for quantum artificial neural networks
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Mitigating Barren Plateaus with Transfer-learning-inspired Parameter Initializations
• Hybrid quantum-classical neural network for calculating ground state energies of molecules
• Quantum Architecture Search with Meta-learning
• Quantum Architecture Search via Deep Reinforcement Learning
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
• Completely Quantum Neural Networks
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• A performance characterization of quantum generative models
• Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
• Warm-Starting and Quantum Computing: A Systematic Mapping Study
• Quantifying Unknown Quantum Entanglement via a Hybrid Quantum-Classical Machine Learning Framework
• Let Quantum Neural Networks Choose Their Own Frequencies
• Hybrid Quantum-Classical Graph Convolutional Network
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• What can we learn from quantum convolutional neural networks?
• Towards Efficient Quantum Hybrid Diffusion Models
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Entanglement assisted training algorithm for supervised quantum classifiers
• Quantum support vector data description for anomaly detection
• Qudit Machine Learning
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Quantum subspace alignment for domain adaptation
• Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
• Investigating the Effect of Noise on the Training Performance of Hybrid Quantum Neural Networks
• SEQUENT: Towards Traceable Quantum Machine Learning using Sequential Quantum Enhanced Training
• Hybrid Quantum-Classical Autoencoders for End-to-End Radio Communication
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Hybrid Quantum Machine Learning Assisted Classification of COVID-19 from Computed Tomography Scans
• Traffic Sign Classification Using Deep and Quantum Neural Networks
• Hybrid Quantum Neural Networks with Variational Quantum Regressor for Enhancing QSPR Modeling of CO2-Capturing Amine
• Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
• Transfer Learning Analysis of Variational Quantum Circuits
• Reinforcement learning to learn quantum states for Heisenberg scaling accuracy
• Expressivity of deterministic quantum computation with one qubit
• Quantum Curriculum Learning
• A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor
• A Hybrid Quantum-Classical Particle-in-Cell Method for Plasma Simulations
• H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading
• Optimal Qubit Mapping Search for Encoding Classical Data into Matrix Product State Representation with Minimal Loss
• A quantum approach for optimal control
• Single-Qudit Quantum Neural Networks for Multiclass Classification
• Exploring exotic configurations with anomalous features using deep learning: Application of classical and quantum-classical hybrid anomaly detection
• Quantum transfer component analysis for domain adaptation
• Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization