Opportunities in Quantum Reservoir Computing and Extreme Learning Machines

Abstract

Quantum reservoir computing (QRC) and quantum extreme learning machines (QELM) are two emerging approaches that have demonstrated their potential both in classical and quantum machine learning tasks. They exploit the quantumness of physical systems combined with an easy training strategy, achieving an excellent performance. The increasing interest in these unconventional computing approaches is fueled by the availability of diverse quantum platforms suitable for implementation and the theoretical progresses in the study of complex quantum systems. In this review article, recent proposals and first experiments displaying a broad range of possibilities are reviewed when quantum inputs, quantum physical substrates and quantum tasks are considered. The main focus is the performance of these approaches, on the advantages with respect to classical counterparts and opportunities.

References in corpus (12)

• The quest for a Quantum Neural Network
• Physical reservoir computing -- An introductory perspective
• Human action recognition with a large-scale brain-inspired photonic computer
• Machine learning meets quantum physics
• Dynamical phase transitions in quantum reservoir computing
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• Reconstructing quantum states with quantum reservoir networks
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Learning Temporal Quantum Tomography
• Introduction to NMR Quantum Information Processing
• Creating and concentrating quantum resource states in noisy environments using a quantum neural network
• Neuromorphic computing with a single qudit

Cited by in corpus (74)

• Experimental quantum memristor
• Dynamical phase transitions in quantum reservoir computing
• Time Series Quantum Reservoir Computing with Weak and Projective Measurements
• Biological neurons act as generalization filters in reservoir computing
• Hybrid quantum-classical reservoir computing of thermal convection flow
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Potential and limitations of quantum extreme learning machines
• Scalable photonic platform for real-time quantum reservoir computing
• Reservoir Computing and Photoelectrochemical Sensors: A Marriage of Convenience
• Complex Quantum Networks: a Topical Review
• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Dissipation as a resource for Quantum Reservoir Computing
• Learning Temporal Quantum Tomography
• Quantum reservoir computation utilising scale-free networks
• Exploring quantum mechanical advantage for reservoir computing
• On fundamental aspects of quantum extreme learning machines
• Quantum reservoir computing in finite dimensions
• Overcoming the Coherence Time Barrier in Quantum Machine Learning on Temporal Data
• Engineered dissipation to mitigate barren plateaus
• How quantum computing can enhance biomarker discovery
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Efficient estimation of trainability for variational quantum circuits
• Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction
• Reduced-order modeling of two-dimensional turbulent Rayleigh-Bénard flow by hybrid quantum-classical reservoir computing
• Solving the time-complexity problem and tuning the performance of quantum reservoir computing by artificial memory restriction
• Harnessing Quantum Extreme Learning Machines for image classification
• Role of coherence in many-body Quantum Reservoir Computing
• Benchmarking the role of particle statistics in Quantum Reservoir Computing
• State estimation with quantum extreme learning machines beyond the scrambling time
• Benefits of Open Quantum Systems for Quantum Machine Learning
• Statistical Complexity of Quantum Learning
• Squeezing as a resource for time series processing in quantum reservoir computing
• Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
• Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
• Impact of the form of weighted networks on the quantum extreme reservoir computation
• Improving the Performance of Echo State Networks Through State Feedback
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• Quantum reservoir computing on random regular graphs
• Quantum memories for squeezed and coherent superpositions in a driven-dissipative nonlinear oscillator
• Quantum reservoir computing for photonic entanglement witnessing
• Entanglement estimation of Werner states with a quantum extreme learning machine
• Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
• Liouvillian skin effect in quantum neural networks
• Multipartite entanglement generation in coupled microcavity arrays
• Practical Trainable Temporal Postprocessor for Multistate Quantum Measurement
• Quantum Reservoir Computing for Realized Volatility Forecasting
• Predicting three-dimensional chaotic systems with four qubit quantum systems
• Non-linear classification capability of quantum neural networks due to emergent quantum metastability
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• An introduction to reservoir computing
• Experimental demonstration of enhanced quantum tomography via quantum reservoir processing
• Generating Quantum Reservoir State Representations with Random Matrices
• Time crystal embodies chimeralike state in periodically driven quantum spin system
• Predicting fermionic densities using a Projected Quantum Kernel method
• High-Accuracy Temporal Prediction via Experimental Quantum Reservoir Computing in Correlated Spins
• Echoes of the Past: A Unified Perspective on Fading memory and Echo States
• Improved Tomographic Estimates by Specialised Neural Networks
• Quantum simulations of complex systems
• Harnessing Quantum Dynamics for Robust and Scalable Quantum Extreme Learning Machines
• All-fiber microendoscopic polarization sensing at single-photon level aided by deep-learning
• Neural networks with quantum states of light
• Quantum fidelity kernel with a trapped-ion simulation platform
• Quantum Transport Reservoir Computing
• Optimal quantum reservoir learning in proximity to universality
• Continuous-variable photonic quantum extreme learning machines for fast collider-data selection
• Unveiling hidden features of the Kitaev model through a complex-network analysis
• Quantum process matrices as images: new tools to design novel denoising methods
• Memory-enhanced quantum extreme learning machines for characterizing non-Markovian dynamics
• Quantum reservoir computing for predicting and characterizing chaotic maps
• Quantum reservoir computing in Jaynes-Cummings models: Nonlinear memory and time-series prediction
• Optical Quantum Computing
• Practical Quantum Reservoir Computing in Rydberg Atom Arrays
• Level Generation with Quantum Reservoir Computing
• Data-driven Quantum Dynamical Embedding Method for Long-term Prediction on Near-term Quantum Computers