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:2506.16332

Feedback-driven recurrent quantum neural network universality

Lukas Gonon, Martínez-Peña, Rodrigo, Juan‐Pablo Ortega

Published Jun 19, 2025• 7 citations
arXivHTMLPDF

Abstract

Quantum reservoir computing uses the dynamics of quantum systems to process temporal data, making it particularly well-suited for machine learning with noisy intermediate-scale quantum devices. Recent developments have introduced feedback-based quantum reservoir systems, which process temporal information with comparatively fewer components and enable real-time computation while preserving the input history. Motivated by their promising empirical performance, in this work, we study the approximation capabilities of feedback-based quantum reservoir computing. More specifically, we are concerned with recurrent quantum neural networks, which are quantum analogues of classical recurrent neural networks. Our results show that regular state-space systems can be approximated using quantum recurrent neural networks without the curse of dimensionality and with the number of qubits only growing logarithmically in the reciprocal of the prescribed approximation accuracy. Notably, our analysis demonstrates that quantum recurrent neural networks are universal with linear readouts, making them both powerful and experimentally accessible. These results pave the way for practical and theoretically grounded quantum reservoir computing with real-time processing capabilities.

DOI
10.48550/arxiv.2506.16332

Related papers

Reservoir Computing via Quantum Recurrent Neural Networks

Samuel Yen-Chi Chen, Daniel Fry, Deshmukh, Amol +2 more

Recent developments in quantum computing and machine learning have propelled the interdisciplinary study of quantum machine learning. Sequential modeling is an important task with high scientific and commercial value. Existing VQC or QNN-based methods require significant computational resources to perform the gradient-based optimization of a larger number of quantum circuit parameters. The major drawback is that such quantum gradient calculation requires a large amount of circuit evaluation, posing challenges in current near-term quantum hardware and simulation software. In this work, we approach sequential modeling by applying a reservoir computing (RC) framework to quantum recurrent neural networks (QRNN-RC) that are based on classical RNN, LSTM and GRU. The main idea to this RC approach is that the QRNN with randomly initialized weights is treated as a dynamical system and only the final classical linear layer is trained. Our numerical simulations show that the QRNN-RC can reach results comparable to fully trained QRNN models for several function approximation and time series prediction tasks. Since the QRNN training complexity is significantly reduced, the proposed model trains notably faster. In this work we also compare to corresponding classical RNN-based RC implementations and show that the quantum version learns faster by requiring fewer training epochs in most cases. Our results demonstrate a new possibility to utilize quantum neural network for sequential modeling with greater quantum hardware efficiency, an important design consideration for noisy intermediate-scale quantum (NISQ) computers.

arXiv:2211.02612•Nov 4, 2022•32 citations

Modular Quantum Recurrent Neural Networks: Scalable Reservoir Computing with High Noise Resilience

Rakesh Sengupta

We introduce a modular architecture for Quantum Recurrent Neural Networks (QRNNs) that reconciles temporal learning with the resource constraints of Noisy Intermediate-Scale Quantum (NISQ) devices. A product-state approximation decomposes Hamiltonian dynamics into locally entangled clusters, yielding an exponential reduction in simulation memory—up to 341× at N = 8 qubits, from $\mathcal{O}\left( {{2^{2N}}} \right)$ to $\mathcal{O}\left( {k\cdot {\text{ }}{2^{2m}}} \right)$ per module—while preserving critical intra-module correlations. Benchmarked on a Quantum Reservoir Computing (QRC) Memory Capacity task, the modular approach retains ≈ 85% of temporal memory capacity at N = 8. At N = 4 it outperforms the monolithic baseline (MC= 0.65 vs. 0.53), revealing a noise compartmentalization effect that shields the reservoir from global decoherence. Zero-Noise Extrapolation (ZNE) recovers single-qubit expectations to within ±0.005, and Trotterized gate-level estimates give 896 CNOTs for N = 8, placing implementation within current NISQ reach.

International Conference on Secure Cyber Computing and Communications (ICSCCC)•May 29, 2026•0 citations

Quantum Reservoir Computing Implementations for Classical and Quantum Problems

Adam Burgess, Marian Florescu

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•8 citations

Recurrent Quantum Feature Maps for Reservoir Computing

Utkarsh Singh, Aaron Z. Goldberg, Christoph Simon +1 more

Reservoir computing promises a fast method for handling large amounts of temporal data. This hinges on constructing a good reservoir--a dynamical system capable of transforming inputs into a high-dimensional representation while remembering properties of earlier data. In this work, we introduce a reservoir based on recurrent quantum feature maps where a fixed quantum circuit is reused to encode both current inputs and a classical feedback signal derived from previous outputs. We evaluate the model on the Mackey-Glass time-series prediction task using our recently introduced CP feature map, and find that it achieves lower mean squared error than standard classical baselines, including echo state networks and multilayer perceptrons, while maintaining compact circuit depth and qubit requirements. We further analyze memory capacity and show that the model effectively retains temporal information, consistent with its forecasting accuracy. Finally, we study the impact of realistic noise and find that performance is robust to several noise channels but remains sensitive to two-qubit gate errors, identifying a key limitation for near-term implementations.

quant-pharXiv:2604.03469•Apr 7, 2026•0 citations

Research and development of a quantum recurrent neural network for learning

S.M. Gushanskiy, Viktor Potapov

Quantum neural network (QNN) is one of the promising areas in which noisy medium-scale quantum devices (MCD) can find advantageous applications in the short term compared to classical resources. Recurrent neural networks are the most fundamental networks for sequential learning, but there is still no canonical model of a quantum recurrent neural network (QRNN), which certainly limits research in the field of quantum deep learning. In the present paper, a new type of QRNS is proposed that would be a good candidate as a canonical QRNN model, where quantum recurrent blocks (QRB) are built in a hardware-efficient way, and QRNN are constructed by stacking QRB in a checkerboard pattern, which can significantly reduce the algorithm’s requirements with respect to coherent time of quantum devices. That is, QRNN is much more accessible on MCD devices. Numerical experiments show that our QRNN provides much better performance in prediction (classification) accuracy compared to classical RNN and state-of-the-art QNN models for sequential training and can predict changing details of time series data.

Informatization and communication•Jan 1, 2023•0 citations

Predicting Chaotic Systems with Quantum Echo-state Networks

Erik Connerty, Ethan N. Evans, Gerasimos Angelatos +1 more

Recent advancements in artificial neural networks have enabled impressive tasks on classical computers, but they demand significant computational resources. While quantum computing offers potential beyond classical systems, the advantages of quantum neural networks (QNNs) remain largely unexplored. In this work, we present and examine a quantum circuit (QC) that implements and aims to improve upon the classical echo-state network (ESN), a type of reservoir-based recurrent neural networks (RNNs), using quantum computers. Typically, ESNs consist of an extremely large reservoir that learns high-dimensional embeddings, enabling prediction of complex system trajectories. Quantum echo-state networks (QESNs) aim to reduce this need for prohibitively large reservoirs by leveraging the unique capabilities of quantum computers, potentially allowing for more efficient and higher performing time-series prediction algorithms. The proposed QESN can be implemented on any digital quantum computer implementing a universal gate set, and does not require any sort of stopping or re-initialization of the circuit, allowing continuous evolution of the quantum state over long time horizons. We conducted simulated QC experiments on the chaotic Lorenz system, both with noisy and noiseless models, to demonstrate the circuit's performance and its potential for execution on noisy intermediate-scale quantum (NISQ) computers.

arXiv:2412.07910•Dec 10, 2024•0 citations
Quantum reservoir computing uses the dynamics of quantum systems to process temporal data, making it particularly well-suited for machine learning with noisy intermediate-scale quantum devices. Recent developments have introduced feedback-based quantum reservoir systems, which process temporal information with comparatively fewer components and enable real-time computation while preserving the input history. Motivated by their promising empirical performance, in this work, we study the approximation capabilities of feedback-based quantum reservoir computing. More specifically, we are concerned with recurrent quantum neural networks, which are quantum analogues of classical recurrent neural networks. Our results show that regular state-space systems can be approximated using quantum recurrent neural networks without the curse of dimensionality and with the number of qubits only growing logarithmically in the reciprocal of the prescribed approximation accuracy. Notably, our analysis demonstrates that quantum recurrent neural networks are universal with linear readouts, making them both powerful and experimentally accessible. These results pave the way for practical and theoretically grounded quantum reservoir computing with real-time processing capabilities.
Recent developments in quantum computing and machine learning have propelled the interdisciplinary study of quantum machine learning. Sequential modeling is an important task with high scientific and commercial value. Existing VQC or QNN-based methods require significant computational resources to perform the gradient-based optimization of a larger number of quantum circuit parameters. The major drawback is that such quantum gradient calculation requires a large amount of circuit evaluation, posing challenges in current near-term quantum hardware and simulation software. In this work, we approach sequential modeling by applying a reservoir computing (RC) framework to quantum recurrent neural networks (QRNN-RC) that are based on classical RNN, LSTM and GRU. The main idea to this RC approach is that the QRNN with randomly initialized weights is treated as a dynamical system and only the final classical linear layer is trained. Our numerical simulations show that the QRNN-RC can reach results comparable to fully trained QRNN models for several function approximation and time series prediction tasks. Since the QRNN training complexity is significantly reduced, the proposed model trains notably faster. In this work we also compare to corresponding classical RNN-based RC implementations and show that the quantum version learns faster by requiring fewer training epochs in most cases. Our results demonstrate a new possibility to utilize quantum neural network for sequential modeling with greater quantum hardware efficiency, an important design consideration for noisy intermediate-scale quantum (NISQ) computers.
We introduce a modular architecture for Quantum Recurrent Neural Networks (QRNNs) that reconciles temporal learning with the resource constraints of Noisy Intermediate-Scale Quantum (NISQ) devices. A product-state approximation decomposes Hamiltonian dynamics into locally entangled clusters, yielding an exponential reduction in simulation memory—up to 341× at N = 8 qubits, from O(22N)\mathcal{O}\left( {{2^{2N}}} \right)O(22N) to O(k⋅ 22m)\mathcal{O}\left( {k\cdot {\text{ }}{2^{2m}}} \right)O(k⋅ 22m) per module—while preserving critical intra-module correlations. Benchmarked on a Quantum Reservoir Computing (QRC) Memory Capacity task, the modular approach retains ≈ 85% of temporal memory capacity at N = 8. At N = 4 it outperforms the monolithic baseline (MC= 0.65 vs. 0.53), revealing a noise compartmentalization effect that shields the reservoir from global decoherence. Zero-Noise Extrapolation (ZNE) recovers single-qubit expectations to within ±0.005, and Trotterized gate-level estimates give 896 CNOTs for N = 8, placing implementation within current NISQ reach.
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 promises a fast method for handling large amounts of temporal data. This hinges on constructing a good reservoir--a dynamical system capable of transforming inputs into a high-dimensional representation while remembering properties of earlier data. In this work, we introduce a reservoir based on recurrent quantum feature maps where a fixed quantum circuit is reused to encode both current inputs and a classical feedback signal derived from previous outputs. We evaluate the model on the Mackey-Glass time-series prediction task using our recently introduced CP feature map, and find that it achieves lower mean squared error than standard classical baselines, including echo state networks and multilayer perceptrons, while maintaining compact circuit depth and qubit requirements. We further analyze memory capacity and show that the model effectively retains temporal information, consistent with its forecasting accuracy. Finally, we study the impact of realistic noise and find that performance is robust to several noise channels but remains sensitive to two-qubit gate errors, identifying a key limitation for near-term implementations.
Quantum neural network (QNN) is one of the promising areas in which noisy medium-scale quantum devices (MCD) can find advantageous applications in the short term compared to classical resources. Recurrent neural networks are the most fundamental networks for sequential learning, but there is still no canonical model of a quantum recurrent neural network (QRNN), which certainly limits research in the field of quantum deep learning. In the present paper, a new type of QRNS is proposed that would be a good candidate as a canonical QRNN model, where quantum recurrent blocks (QRB) are built in a hardware-efficient way, and QRNN are constructed by stacking QRB in a checkerboard pattern, which can significantly reduce the algorithm’s requirements with respect to coherent time of quantum devices. That is, QRNN is much more accessible on MCD devices. Numerical experiments show that our QRNN provides much better performance in prediction (classification) accuracy compared to classical RNN and state-of-the-art QNN models for sequential training and can predict changing details of time series data.
Recent advancements in artificial neural networks have enabled impressive tasks on classical computers, but they demand significant computational resources. While quantum computing offers potential beyond classical systems, the advantages of quantum neural networks (QNNs) remain largely unexplored. In this work, we present and examine a quantum circuit (QC) that implements and aims to improve upon the classical echo-state network (ESN), a type of reservoir-based recurrent neural networks (RNNs), using quantum computers. Typically, ESNs consist of an extremely large reservoir that learns high-dimensional embeddings, enabling prediction of complex system trajectories. Quantum echo-state networks (QESNs) aim to reduce this need for prohibitively large reservoirs by leveraging the unique capabilities of quantum computers, potentially allowing for more efficient and higher performing time-series prediction algorithms. The proposed QESN can be implemented on any digital quantum computer implementing a universal gate set, and does not require any sort of stopping or re-initialization of the circuit, allowing continuous evolution of the quantum state over long time horizons. We conducted simulated QC experiments on the chaotic Lorenz system, both with noisy and noiseless models, to demonstrate the circuit's performance and its potential for execution on noisy intermediate-scale quantum (NISQ) computers.