High-Accuracy Temporal Prediction via Experimental Quantum Reservoir Computing in Correlated Spins

Abstract

Physical reservoir computing provides a powerful machine learning paradigm that exploits nonlinear physical dynamics for efficient information processing. By incorporating quantum effects, quantum reservoir computing offers superior potential for machine learning applications, as quantum dynamics are exponentially costly to simulate classically. Here, we present a novel quantum reservoir computing approach based on correlated quantum spin systems, exploiting natural quantum many-body interactions to generate reservoir dynamics, thereby circumventing the practical challenges of deep quantum circuits. Our experimental implementation supports nontrivial quantum entanglement and exhibits sufficient dynamical complexity for high-performance machine learning. We achieve state-of-the-art performance in experiments on standard time-series benchmarks, reducing prediction error by 1 to 2 orders of magnitude compared to previous quantum reservoir experiments. In long-term weather forecasting, our 9-spin quantum reservoir delivers greater prediction accuracy than classical reservoirs with thousands of nodes. This represents the first experimental demonstration of quantum machine learning outperforming large-scale classical models on real-world tasks.

References in corpus (35)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Quantum computational advantage using photons
• Recent Advances in Physical Reservoir Computing: A Review
• Observation of a Discrete Time Crystal
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• Data re-uploading for a universal quantum classifier
• Vowel recognition with four coupled spin-torque nano-oscillators
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum Many-Body Scars and Weak Breaking of Ergodicity
• Generalization in quantum machine learning from few training data
• Physical reservoir computing -- An introductory perspective
• Observing single quantum trajectories of a superconducting qubit
• Harnessing disordered quantum dynamics for machine learning
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Dynamical phase transitions in quantum reservoir computing
• Temporal Information Processing on Noisy Quantum Computers
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• Efficient Quantum State Estimation by Continuous Weak Measurement and Dynamical Control
• Time Series Quantum Reservoir Computing with Weak and Projective Measurements
• Natural quantum reservoir computing for temporal information processing
• Simultaneous tracking of spin angle and amplitude beyond classical limits
• Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems
• Hybrid quantum-classical reservoir computing of thermal convection flow
• Dissipation as a resource for Quantum Reservoir Computing
• The Reservoir Learning Power across Quantum Many-Boby Localization Transition
• Feedback-driven quantum reservoir computing for time-series analysis
• Quantum reservoir computing in finite dimensions
• Overcoming the Coherence Time Barrier in Quantum Machine Learning on Temporal Data
• Quantum reservoir probing of quantum phase transitions
• Dynamical Quantum Tomography
• Quantum reservoir probing: an inverse paradigm of quantum reservoir computing for exploring quantum many-body physics

Cited by in corpus (1)

• Quantum reservoir computing in Jaynes-Cummings models: Nonlinear memory and time-series prediction