Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2209.03221

Quantum reservoir neural network implementation on coherently coupled quantum oscillators

Julien Dudas, Baptiste Carles, Erwan Plouet, Frank Alice Mizrahi, Julie Grollier, Danijela Marković

Published Sep 7, 2022• 0 citations
arXivHTMLPDF

Abstract

Quantum reservoir computing is a promising approach for quantum neural networks, capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits suffer from limited connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyse a specific hardware implementation based on superconducting circuits: with just two coupled quantum oscillators, we create a quantum reservoir comprising up to 81 neurons. We obtain state-of-the-art accuracy of 99 % on benchmark tasks that otherwise require at least 24 classical oscillators to be solved. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computing, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures, with billions of neurons implemented with only 10 coupled quantum oscillators.

DOI
10.48550/arxiv.2209.03221

Related papers

Quantum reservoir computing implementation on coherently coupled quantum oscillators

Julien Dudas, Baptiste Carles, Erwan Plouet +3 more

Abstract Quantum reservoir computing is a promising approach for quantum neural networks, capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits suffer from limited connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyze a specific hardware implementation based on superconducting circuits: with just two coupled quantum oscillators, we create a quantum reservoir comprising up to 81 neurons. We obtain state-of-the-art accuracy of 99% on benchmark tasks that otherwise require at least 24 classical oscillators to be solved. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computing, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures, with billions of neurons implemented with only 10 coupled quantum oscillators.

npj Quantum Information•Jul 7, 2023•69 citations

Quantum reservoir neural network implementation on a Josephson mixer

Julien Dudas, Erwan Plouet, Frank Alice Mizrahi +2 more

Quantum reservoir computing is a promising approach to quantum neural networks capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits are limited by low connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyse a specific hardware implementation based on superconducting circuits. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computation, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures.

•Nov 3, 2022•0 citations

Experimental quantum reservoir computing with a circuit-quantum-electrodynamics system

Baptiste Carles, Julien Dudas, Léo Balembois +2 more

Quantum reservoir computing is a machine-learning framework that offers ease of training compared to other quantum neural networks, as it does not rely on gradient-based optimization. Learning is performed in a single step on the output features measured from the quantum system. Various implementations of quantum reservoir computing have been explored in simulations, with different measured features. Although simulations have shown that quantum reservoirs present advantages in performance compared to classical reservoirs, experimental implementations have remained scarce. This is due to the challenge of obtaining a large number of output features that are nonlinear transformations of the input data. In this work, we show that even with a circuit quantum electrodynamics system as simple as a single transmon coupled to a readout resonator, we can implement a proof-of-concept realization of quantum reservoir computing. We obtain a large number of nonlinear features from a single physical system by encoding the input data in the amplitude of a coherent drive and measuring the cavity state in the Fock basis. We demonstrate classification of two classical tasks with significantly smaller hardware resources and fewer measured features compared to classical neural networks. Our experimental results are supported by numerical simulations that show additional Kerr nonlinearity is beneficial to reservoir performance. Our work demonstrates a hardware-efficient quantum neural-network implementation that can be further scaled up and generalized to other quantum machine-learning models.

arXiv:2506.22016•Physical Review Applied•Feb 2, 2026•0 citations

Quantum Reservoir Computing Implementations for Classical and Quantum Problems

Adam Burgess, Marian Florescu A

Quantum reservoir computing has emerged as a promising paradigm within the field of quantum machine learning, harnessing the inherent properties of quantum systems to optimise and enhance information processing capabilities. Here, we explore the potential of quantum-inspired machine learning methodologies by leveraging the complex dynamics of quantum reservoirs to address computationally challenging tasks with enhanced efficiency and accuracy. To this end, we employ an open quantum system model comprising two-level atomic ensembles coupled to Lorentzian photonic cavities to construct a quantum physical reservoir computer layer for a recurrent neural network. We evaluate the effectiveness of this approach by applying it to a standard machine learning image-recognition problem and benchmarking its performance against a conventional neural network of similar architecture, but lacking the quantum physical reservoir computer layer. Remarkably, as the dataset size increases, the quantum physical reservoir computer outperforms the conventional neural network, requiring fewer training epochs and a smaller dataset to achieve comparable accuracy. Furthermore, we employ the quantum physical reservoir computing approach to model the dynamics of open quantum systems, focusing on atomic system ensembles interacting with a structured photonic reservoir associated with a photonic band-gap material. Our results reveal that the quantum reservoir computer provides equally powerful representations for quantum dynamical problems, maintaining effectiveness even under constraints of limited training data.

arXiv:2211.08567•Nov 15, 2022•1 citation

Entanglement classification of Gaussian and non-Gaussian states with quantum reservoir computing

Johannes Annala

Reservoir computing is a neural network framework capable of nonlinear information processing. The ambiguous nature of the information processing unit provides a fascinating opportunity of employing physical systems as reservoirs. This has also spiked an interest in the research and development of quantum systems. As quantum computing still faces many problems such as scalability and the loss of coherence, quantum reservoir computing offers an alternative way of conducting intricate quantum tasks. These results are not limited to quantum tasks, as the evidence in quantum reservoir computing suggest a possible advantage over classical algorithms in classical nonlinear tasks. This work provides a comprehensive inspection of the theory behind quantum reservoir computing and an entanglement classification task conducted on the reservoir. This includes the review of tools for the measurement of entanglement, Gaussian and non-Gaussian nature of systems, machine learning and quantum computing. The theoretical review is accompanied by results of classical reservoir computing and a greater research on the capabilities of different quantum substrates used in quantum reservoir computing. The main part of this work is to build a working quantum reservoir computing system containing a fermionic reservoir. The task of the reservoir is to learn to classify quantum entanglement of two-mode bosonic inputs. The bosonic inputs used in this work are squeezed thermal states, photon added squeezed vacuum states, photon subtracted squeezed vacuum states and number states. This way Gaussian and non-Gaussian entanglement recognition is tested. Reservoirs of sizes 2, 3 and 4 modes are used and different connectivities inside the reservoir networks are studied. Even though the entanglement is assessed for different classes of states, the training is conducted with only squeezed thermal states

•May 27, 2026•0 citations

Hilbert space as a computational resource in reservoir computing

William D. Kalfus, Guilhem J. Ribeill, Graham E. Rowlands +3 more

Accelerating computation with quantum resources is limited by the challenges of high-fidelity control of quantum systems. Reservoir computing presents an attractive alternative, as precise control and full calibration of system dynamics are not required. Instead, complex internal trajectories in a large state space are leveraged as a computational resource. Quantum systems offer a unique venue for reservoir computing, given the presence of interactions unavailable in classical systems and a potentially exponentially-larger computational space. With a reservoir comprised of a single $d$-dimensional quantum system, we demonstrate clear performance improvement with Hilbert space dimension at two benchmark tasks and advantage over the physically analogous classical reservoir. Quantum reservoirs as realized by current-era quantum hardware offer immediate practical implementation and a promising outlook for increased performance in larger systems.

Physical Review Research•Jul 5, 2022•31 citations
Quantum reservoir computing is a promising approach for quantum neural networks, capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits suffer from limited connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyse a specific hardware implementation based on superconducting circuits: with just two coupled quantum oscillators, we create a quantum reservoir comprising up to 81 neurons. We obtain state-of-the-art accuracy of 99 % on benchmark tasks that otherwise require at least 24 classical oscillators to be solved. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computing, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures, with billions of neurons implemented with only 10 coupled quantum oscillators.
Abstract Quantum reservoir computing is a promising approach for quantum neural networks, capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits suffer from limited connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyze a specific hardware implementation based on superconducting circuits: with just two coupled quantum oscillators, we create a quantum reservoir comprising up to 81 neurons. We obtain state-of-the-art accuracy of 99% on benchmark tasks that otherwise require at least 24 classical oscillators to be solved. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computing, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures, with billions of neurons implemented with only 10 coupled quantum oscillators.
Quantum reservoir computing is a promising approach to quantum neural networks capable of solving hard learning tasks on both classical and quantum input data. However, current approaches with qubits are limited by low connectivity. We propose an implementation for quantum reservoir that obtains a large number of densely connected neurons by using parametrically coupled quantum oscillators instead of physically coupled qubits. We analyse a specific hardware implementation based on superconducting circuits. Our results give the coupling and dissipation requirements in the system and show how they affect the performance of the quantum reservoir. Beyond quantum reservoir computation, the use of parametrically coupled bosonic modes holds promise for realizing large quantum neural network architectures.
Quantum reservoir computing is a machine-learning framework that offers ease of training compared to other quantum neural networks, as it does not rely on gradient-based optimization. Learning is performed in a single step on the output features measured from the quantum system. Various implementations of quantum reservoir computing have been explored in simulations, with different measured features. Although simulations have shown that quantum reservoirs present advantages in performance compared to classical reservoirs, experimental implementations have remained scarce. This is due to the challenge of obtaining a large number of output features that are nonlinear transformations of the input data. In this work, we show that even with a circuit quantum electrodynamics system as simple as a single transmon coupled to a readout resonator, we can implement a proof-of-concept realization of quantum reservoir computing. We obtain a large number of nonlinear features from a single physical system by encoding the input data in the amplitude of a coherent drive and measuring the cavity state in the Fock basis. We demonstrate classification of two classical tasks with significantly smaller hardware resources and fewer measured features compared to classical neural networks. Our experimental results are supported by numerical simulations that show additional Kerr nonlinearity is beneficial to reservoir performance. Our work demonstrates a hardware-efficient quantum neural-network implementation that can be further scaled up and generalized to other quantum machine-learning models.
Quantum reservoir computing has emerged as a promising paradigm within the field of quantum machine learning, harnessing the inherent properties of quantum systems to optimise and enhance information processing capabilities. Here, we explore the potential of quantum-inspired machine learning methodologies by leveraging the complex dynamics of quantum reservoirs to address computationally challenging tasks with enhanced efficiency and accuracy. To this end, we employ an open quantum system model comprising two-level atomic ensembles coupled to Lorentzian photonic cavities to construct a quantum physical reservoir computer layer for a recurrent neural network. We evaluate the effectiveness of this approach by applying it to a standard machine learning image-recognition problem and benchmarking its performance against a conventional neural network of similar architecture, but lacking the quantum physical reservoir computer layer. Remarkably, as the dataset size increases, the quantum physical reservoir computer outperforms the conventional neural network, requiring fewer training epochs and a smaller dataset to achieve comparable accuracy. Furthermore, we employ the quantum physical reservoir computing approach to model the dynamics of open quantum systems, focusing on atomic system ensembles interacting with a structured photonic reservoir associated with a photonic band-gap material. Our results reveal that the quantum reservoir computer provides equally powerful representations for quantum dynamical problems, maintaining effectiveness even under constraints of limited training data.
Reservoir computing is a neural network framework capable of nonlinear information processing. The ambiguous nature of the information processing unit provides a fascinating opportunity of employing physical systems as reservoirs. This has also spiked an interest in the research and development of quantum systems. As quantum computing still faces many problems such as scalability and the loss of coherence, quantum reservoir computing offers an alternative way of conducting intricate quantum tasks. These results are not limited to quantum tasks, as the evidence in quantum reservoir computing suggest a possible advantage over classical algorithms in classical nonlinear tasks. This work provides a comprehensive inspection of the theory behind quantum reservoir computing and an entanglement classification task conducted on the reservoir. This includes the review of tools for the measurement of entanglement, Gaussian and non-Gaussian nature of systems, machine learning and quantum computing. The theoretical review is accompanied by results of classical reservoir computing and a greater research on the capabilities of different quantum substrates used in quantum reservoir computing. The main part of this work is to build a working quantum reservoir computing system containing a fermionic reservoir. The task of the reservoir is to learn to classify quantum entanglement of two-mode bosonic inputs. The bosonic inputs used in this work are squeezed thermal states, photon added squeezed vacuum states, photon subtracted squeezed vacuum states and number states. This way Gaussian and non-Gaussian entanglement recognition is tested. Reservoirs of sizes 2, 3 and 4 modes are used and different connectivities inside the reservoir networks are studied. Even though the entanglement is assessed for different classes of states, the training is conducted with only squeezed thermal states
Accelerating computation with quantum resources is limited by the challenges of high-fidelity control of quantum systems. Reservoir computing presents an attractive alternative, as precise control and full calibration of system dynamics are not required. Instead, complex internal trajectories in a large state space are leveraged as a computational resource. Quantum systems offer a unique venue for reservoir computing, given the presence of interactions unavailable in classical systems and a potentially exponentially-larger computational space. With a reservoir comprised of a single ddd-dimensional quantum system, we demonstrate clear performance improvement with Hilbert space dimension at two benchmark tasks and advantage over the physically analogous classical reservoir. Quantum reservoirs as realized by current-era quantum hardware offer immediate practical implementation and a promising outlook for increased performance in larger systems.