Quantum Wiener architecture for quantum reservoir computing
Open Access
- 22 June 2026
- journal article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 114 (1)
Abstract
This work focuses on quantum reservoir computing and, in particular, on quantum Wiener architectures (qWiener), consisting of quantum linear dynamic networks with weak continuous measurements and classical nonlinear static readouts. We provide the first rigorous proof that qWiener systems retain the fading-memory property and universality of classical Wiener architectures, despite quantum constraints on linear dynamics and measurement backaction. Furthermore, we develop a kernel-theoretic interpretation showing that qWiener reservoirs naturally induce deep kernels, providing a principled framework for analyzing their expressivity. We further characterize the simplest qWiener instantiation, consisting of concatenated quantum harmonic oscillators, and show the difference with respect to the classical case. Finally, we empirically evaluate the architecture on standard reservoir computing benchmarks, demonstrating systematic performance gains over prior classical and quantum reservoir computing models.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Linear quantum systems: A tutorialAnnual Reviews in Control, 2022
- Opportunities in Quantum Reservoir Computing and Extreme Learning MachinesAdvanced Quantum Technologies, 2021
- dynoNet: A neural network architecture for learning dynamical systemsInternational Journal of Adaptive Control and Signal Processing, 2021
- Information Processing Capacity of Spin-Based Quantum Reservoir Computing SystemsCognitive Computation, 2020
- Kernel methods in system identification, machine learning and function estimation: A surveyAutomatica, 2014
- On the estimation of transfer functions, regularizations and Gaussian processes—RevisitedAutomatica, 2012
- Optimal State Estimation2006
- Monte Carlo Statistical Methods2004
- Quantum Noise2000
- Quantum Communications and Measurement1995