Harnessing Quantum Extreme Learning Machines for image classification

Abstract

Interest in quantum machine learning is increasingly growing due to its potential to offer more efficient solutions for problems that are difficult to tackle with classical methods. In this context, the research work presented here focuses on the use of quantum machine learning techniques for image classification tasks. We exploit a quantum extreme learning machine by taking advantage of its rich feature map provided by the quantum reservoir substrate. We systematically analyse different phases of the quantum extreme learning machine process, from the dataset preparation to the image final classification. In particular, we have tested different encodings, together with Principal Component Analysis, the use of Auto-Encoders, as well as the dynamics of the model through the use of different Hamiltonians for the quantum reservoir. Our results show that the introduction of a quantum reservoir systematically improves the accuracy of the classifier. Additionally, while different encodings can lead to significantly different performances, Hamiltonians with varying degrees of connectivity exhibit the same discrimination rate, provided they are interacting.

17 pages, 8 figures

References in corpus (47)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• QuTiP 2: A Python framework for the dynamics of open quantum systems
• Quantum computational advantage using photons
• Recent Advances in Physical Reservoir Computing: A Review
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• Quantum Convolutional Neural Networks
• Quantum algorithms: an overview
• The quest for a Quantum Neural Network
• Next Generation Reservoir Computing
• Quantum advantage in learning from experiments
• Quantum computing with neutral atoms
• Quantum convolutional neural network for classical data classification
• Robust data encodings for quantum classifiers
• Harnessing disordered quantum dynamics for machine learning
• Hierarchical quantum classifiers
• Quantum reservoir processing
• Quantum machine learning for image classification
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Boosting computational power through spatial multiplexing in quantum reservoir computing
• Quantum reservoir computing with a single nonlinear oscillator
• Dynamical phase transitions in quantum reservoir computing
• Temporal Information Processing on Noisy Quantum Computers
• Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
• Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems
• Hybrid quantum-classical reservoir computing of thermal convection flow
• Potential and limitations of quantum extreme learning machines
• Realising and compressing quantum circuits with quantum reservoir computing
• Reservoir Computing Approach to Quantum State Measurement
• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Learning Nonlinear Input-Output Maps with Dissipative Quantum Systems
• Dissipation as a resource for Quantum Reservoir Computing
• Assessing Quantum Computing Performance for Energy Optimization in a Prosumer Community
• Feedback-driven quantum reservoir computing for time-series analysis
• Quantum reservoir computation utilising scale-free networks
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• On fundamental aspects of quantum extreme learning machines
• Quantum Capsule Networks
• Exploring quantum mechanical advantage for reservoir computing
• Variational Gibbs State Preparation on NISQ devices
• Variational Quantum Algorithms for the Allocation of Resources in a Cloud/Edge Architecture
• Benchmarking the role of particle statistics in Quantum Reservoir Computing
• State estimation with quantum extreme learning machines beyond the scrambling time
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Quantum Reservoir Computing for Speckle-Disorder Potentials

Cited by in corpus (6)

• Predicting fermionic densities using a Projected Quantum Kernel method
• Assessing Projected Quantum Kernels for the Classification of IoT Data
• Harnessing Quantum Dynamics for Robust and Scalable Quantum Extreme Learning Machines
• Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training
• Memory-enhanced quantum extreme learning machines for characterizing non-Markovian dynamics
• Quantum reservoir computing for predicting and characterizing chaotic maps