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

IEEE Access

Neural Network-Based Discriminators for Single-Shot Readout of Superconducting Qubits in Non-Gaussian Conditions

Abdalkarim Awad

Published Jan 1, 2026• 0 citations
Publisher

Abstract

Single-shot dispersive readout of superconducting qubits is a very important part of real-time quantum feedback and quantum error correction (QEC). Conventional discriminators such as thresholding and matched filtering are optimal under Gaussian noise assumptions, yet performance degrades in the presence of non-Gaussian effects in particular when including energy relaxation during readout and leakage to non-computational states. Neural network based discriminators have been proposed to mitigate these limitations. There is still a lack of characterization of the scenarios in which they offer a significant benefit and the mechanisms that underlie that advantage. This paper shows a controlled simulation study of six discrimination methods that get more detailed as the model gets more complex: thresholding, matched filtering, linear discriminant analysis, a multilayer perceptron operating on integrated in-phase and quadrature (IQ) features, one-dimensional convolutional neural network operating on the full time-resolved measurement trace, and a hybrid CNN. By systematically varying physically relevant parameters, we map classifier performance as a function of the ratio of readout duration to qubit relaxation time, which governs the strength of non-Gaussian effects. We demonstrate that neural network-based discriminators offer minimal or no benefits in Gaussian-dominated contexts where linear approaches are almost optimal, yet produce substantial enhancements when non-Gaussian effects are present. Specifically, a hybrid architecture combining a small temporal CNN branch with a direct skip connection for the integrated IQ features achieves assignment fidelity of about 0.98 in the stress-test scenario, which represents a significant improvement over the matched filter. This hybrid architecture, at only 686 trainable parameters, is smaller than the pure CNN yet dominates it in easy settings (where the pure CNN underperforms linear baselines by $\approx 6$ percentage points, pp) while retaining its advantage in hard settings. Additionally, confusion-matrix analysis reveals that this enhancement results from the capacity of temporal models to leverage within-window dynamics that are unavailable to classifiers utilizing integrated observations. Rather than recommending the hybrid as a universally superior method, we characterise the regime in which it helps: it trails the matched filter by only $\approx 1.2$ pp in Gaussian conditions while providing a + 5.39 pp advantage in the stress-test regime, which makes it a regime-robust default wherever the operating point is uncertain or leakage is a meaningful error channel. These results provide a predictive understanding of when neural-network-based readout is beneficial and offer practical guidance for selecting discrimination strategies in superconducting qubit systems subject to real-time constraints.

DOI
10.1109/access.2026.3722871

Related papers

Real-time single-shot qubit-state discrimination on FPGA with a parameter-efficient Trace–IQ fusion network

Abdalkarim Awad

Abstract Fast, high-fidelity single-shot readout is a prerequisite for real-time feedback in superconducting-qubit processors, yet the matched filter that remains the field standard discards the temporal structure of the dispersive readout signal and degrades in the presence of energy decay, leakage, and slow parameter drift. We study neural-network discriminators that can run inside the readout feedback loop on a field-programmable gate array (FPGA). Using a physically motivated simulation of dispersive readout that includes cavity ring-up, T1 decay during measurement, leakage to the second excited state, slow IQ drift, and finite signal-to-noise ratio, we benchmark four classical baselines (boxcar integration, matched filtering, linear discriminant analysis, and a Gaussian mixture model) against a floating-point convolutional neural network (CNN), a quantization-aware CNN trained with QKeras, and a new hybrid architecture, the Trace–IQ Fusion Network (TIF-Net), that fuses a learned temporal feature extractor with an integrated-IQ skip path. TIF-Net reachesan assignment fidelity of 0.9962 with only 686 trainable parameters, roughlyan order of magnitude fewer than the 7194-parameter CNN, while exceedingthe matched-filter baseline by 2.3 percentage points. The architecture is constructed to be synthesis-safe: the two pooling operations are realised as fixed-weight convolutions, which we show avoids a scaling pathology of the pooling primitives in our high-level-synthesis (HLS) toolchain. A weight bit-width sweep shows that both networks retain near-peak fidelity down to 4-bit weights, indicating a small multiplier budget for on-board deployment.

•Aug 19, 2026•0 citations

Spiking neural networks for streaming qubit readout

Barry M. Dillon, Aqib Javed, Jim Harkin +2 more

Fast and accurate qubit-state assignment is essential for feedback, calibration, and error correction in quantum processors. In superconducting platforms, frequency-multiplexed readout makes this task intrinsically multivariate as measured traces can encode crosstalk, qubit-state relaxation events, and other transient nonidealities that are not fully captured by conventional matched filtering. Here, we introduce spiking neural network (SNN) discriminators for superconducting qubit readout. By processing the measurement window in successive time chunks, the networks exploit temporal structure and update classification scores as data arrive, rather than waiting until the end of the readout window. The spiking networks outperform matched-filter discrimination and approach the accuracy of a full-trace artificial neural network. Beyond reaching the performance of artificial neural networks, the key advantage of SNNs is that they provide a streaming, time-resolved estimate of the qubit state that evolves as the readout signal is acquired. Using quantisation-aware training and hls4ml synthesis, we further demonstrate that each FPGA inference update can be completed before the next readout chunk arrives. These results establish spiking neural networks as a promising route to low-latency, real-time qubit readout on FPGA hardware, with broader implications for time-critical quantum-control and scientific-inference applications.

quant-pharXiv:2610.02129•Oct 2, 2026•0 citations

Robust and fast post-processing of single-shot spin qubit detection events with a neural network

Tom Struck, Javed Lindner, Arne Hollmann +4 more

Abstract Establishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

arXiv:2012.04686•Scientific Reports•Aug 10, 2021•16 citations

A Hybrid Quantum–Classical Deep Learning Approach for Image Recognition: Performance Analysis of Quanvolution-Based Convolutional Models

James William Carter, Emily Rose Thompson

The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.

International Journal of Intelligent Data and Machine Learning•Jun 1, 2026•0 citations

Time-series based quantum state discrimination

Samuel Jung, Neel Vora, Akel Hashim +2 more

Abstract Measurement errors in quantum computers are very detrimental to quantum computations. The ability to efficiently and accurately readout quantum states is crucial for quantum error correction schemes and quantum algorithms. Readout fidelity is typically limited by a poor signal-to-noise (SNR) ratio between the quantum states we intend to classify, as well as energy relaxation (e.g., $T_1$ decay) from an excited state to a lower state during readout. Superconducting quantum bits (qubit), one of the leading candidates for scalable quantum computing hardware, are particularly limited by energy relaxation due to their relatively short coherence times. While most approaches for classifying the results of readout on superconducting qubits typically utilize clustering algorithms (e.g., a Gaussian mixture model) on integrated readout signals, these cannot distinguish between a quantum bit that was in the ground state prior to measurement from a qubit that decays to the ground state during measurement. For this reason, we instead propose using machine learning (ML) on the raw (non-integrated) analog signal and classification models on the full time series data (i.e., the \emph{trajectory}). We observe that time series classification methods, such as our chosen long short-term memory (LSTM) model, in combination with filtering and feature engineering techniques, consistently outperform clustering models. In particular, we find that the largest improvements come from reclassifying points in the boundary regions between neighboring clusters. These boundary points correspond to measurement records that deviate from the typical cluster, likely due to transient or noisy features in the signal that are not captured when the data is integrated. By retaining temporal information, sequence-aware models such as LSTMs can better discriminate these trajectories, whereas clustering methods based on integrated values are more prone to misclassifications.

•Apr 13, 2026•0 citations

Multi-Stage Mamba-Based Architecture for Fast and Scalable Superconducting Qubit Readout

Luca Otting, Xiaorang Guo, Emmanouil Giortamis +3 more

Reliable qubit readout is a critical bottleneck toward fault-tolerant quantum computing (FTQC). In superconducting quantum processors, readout operations are both error-prone and high-latency. These challenges become more severe in frequency-multiplexed architectures, where signal crosstalk among neighboring qubits significantly degrades readout fidelity. Existing machine learning (ML)-based approaches rely on feed-forward neural networks (FNNs) that suffer from large parameter sizes and lack an end-to-end network that jointly addresses relaxation errors and discriminates qubit states. In this work, we present a multi-stage qubit state discriminator based on the Mamba model, which enables efficient sequence modeling with linear complexity. The first stage performs initial state discrimination, followed by a refinement stage that identifies and mitigates relaxation-induced errors. Our lightweight model achieves a geometric mean readout fidelity of 0.906, outperforming the best-reported state-of-the-art method while reducing parameter size by 49.6%; our optimal model further reaches 0.911. Both models remain robust across varying input trace lengths, maintaining a high fidelity of 0.893 at readout durations as short as 500 $ns$, achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).

quant-pharXiv:2607.11668•Jul 14, 2026•0 citations
Single-shot dispersive readout of superconducting qubits is a very important part of real-time quantum feedback and quantum error correction (QEC). Conventional discriminators such as thresholding and matched filtering are optimal under Gaussian noise assumptions, yet performance degrades in the presence of non-Gaussian effects in particular when including energy relaxation during readout and leakage to non-computational states. Neural network based discriminators have been proposed to mitigate these limitations. There is still a lack of characterization of the scenarios in which they offer a significant benefit and the mechanisms that underlie that advantage. This paper shows a controlled simulation study of six discrimination methods that get more detailed as the model gets more complex: thresholding, matched filtering, linear discriminant analysis, a multilayer perceptron operating on integrated in-phase and quadrature (IQ) features, one-dimensional convolutional neural network operating on the full time-resolved measurement trace, and a hybrid CNN. By systematically varying physically relevant parameters, we map classifier performance as a function of the ratio of readout duration to qubit relaxation time, which governs the strength of non-Gaussian effects. We demonstrate that neural network-based discriminators offer minimal or no benefits in Gaussian-dominated contexts where linear approaches are almost optimal, yet produce substantial enhancements when non-Gaussian effects are present. Specifically, a hybrid architecture combining a small temporal CNN branch with a direct skip connection for the integrated IQ features achieves assignment fidelity of about 0.98 in the stress-test scenario, which represents a significant improvement over the matched filter. This hybrid architecture, at only 686 trainable parameters, is smaller than the pure CNN yet dominates it in easy settings (where the pure CNN underperforms linear baselines by ≈6\approx 6≈6 percentage points, pp) while retaining its advantage in hard settings. Additionally, confusion-matrix analysis reveals that this enhancement results from the capacity of temporal models to leverage within-window dynamics that are unavailable to classifiers utilizing integrated observations. Rather than recommending the hybrid as a universally superior method, we characterise the regime in which it helps: it trails the matched filter by only ≈1.2\approx 1.2≈1.2 pp in Gaussian conditions while providing a + 5.39 pp advantage in the stress-test regime, which makes it a regime-robust default wherever the operating point is uncertain or leakage is a meaningful error channel. These results provide a predictive understanding of when neural-network-based readout is beneficial and offer practical guidance for selecting discrimination strategies in superconducting qubit systems subject to real-time constraints.
Abstract Fast, high-fidelity single-shot readout is a prerequisite for real-time feedback in superconducting-qubit processors, yet the matched filter that remains the field standard discards the temporal structure of the dispersive readout signal and degrades in the presence of energy decay, leakage, and slow parameter drift. We study neural-network discriminators that can run inside the readout feedback loop on a field-programmable gate array (FPGA). Using a physically motivated simulation of dispersive readout that includes cavity ring-up, T1 decay during measurement, leakage to the second excited state, slow IQ drift, and finite signal-to-noise ratio, we benchmark four classical baselines (boxcar integration, matched filtering, linear discriminant analysis, and a Gaussian mixture model) against a floating-point convolutional neural network (CNN), a quantization-aware CNN trained with QKeras, and a new hybrid architecture, the Trace–IQ Fusion Network (TIF-Net), that fuses a learned temporal feature extractor with an integrated-IQ skip path. TIF-Net reachesan assignment fidelity of 0.9962 with only 686 trainable parameters, roughlyan order of magnitude fewer than the 7194-parameter CNN, while exceedingthe matched-filter baseline by 2.3 percentage points. The architecture is constructed to be synthesis-safe: the two pooling operations are realised as fixed-weight convolutions, which we show avoids a scaling pathology of the pooling primitives in our high-level-synthesis (HLS) toolchain. A weight bit-width sweep shows that both networks retain near-peak fidelity down to 4-bit weights, indicating a small multiplier budget for on-board deployment.
Fast and accurate qubit-state assignment is essential for feedback, calibration, and error correction in quantum processors. In superconducting platforms, frequency-multiplexed readout makes this task intrinsically multivariate as measured traces can encode crosstalk, qubit-state relaxation events, and other transient nonidealities that are not fully captured by conventional matched filtering. Here, we introduce spiking neural network (SNN) discriminators for superconducting qubit readout. By processing the measurement window in successive time chunks, the networks exploit temporal structure and update classification scores as data arrive, rather than waiting until the end of the readout window. The spiking networks outperform matched-filter discrimination and approach the accuracy of a full-trace artificial neural network. Beyond reaching the performance of artificial neural networks, the key advantage of SNNs is that they provide a streaming, time-resolved estimate of the qubit state that evolves as the readout signal is acquired. Using quantisation-aware training and hls4ml synthesis, we further demonstrate that each FPGA inference update can be completed before the next readout chunk arrives. These results establish spiking neural networks as a promising route to low-latency, real-time qubit readout on FPGA hardware, with broader implications for time-critical quantum-control and scientific-inference applications.
Abstract Establishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.
The integration of quantum computing principles with classical deep learning architectures has emerged as a promising direction for advancing image recognition systems beyond the limitations of purely classical convolutional neural networks (CNNs). This study proposes and analyzes a hybrid quantum–classical deep learning framework based on quanvolutional neural network (QNN) principles, where quantum circuits are embedded within convolutional feature extraction layers to enhance representation capability. The research investigates how quantum-enhanced filters, particularly quanvolutional layers, contribute to improved feature diversity, non-linear transformation capacity, and classification accuracy in image recognition tasks. Building upon established convolutional architectures and quantum machine learning theories, the proposed framework integrates quantum random circuit encoding with classical deep neural networks to evaluate performance gains in comparison to conventional CNN models. The study further incorporates theoretical insights from hybrid quantum-classical learning systems, emphasizing the role of parameterized quantum circuits in feature mapping and optimization stability. The methodology is grounded in NISQ-era quantum computing constraints and leverages hybrid optimization strategies to ensure computational feasibility. Experimental evaluation demonstrates that quanvolution-based models can provide improved robustness in feature extraction, particularly in high-dimensional image spaces, while maintaining competitive computational efficiency. However, scalability limitations and noise sensitivity in quantum circuits remain key challenges. Overall, this work contributes to the growing field of quantum-enhanced machine learning by providing a structured performance analysis of hybrid quanvolutional architectures and highlighting their potential role in next-generation intelligent visual recognition systems.
Abstract Measurement errors in quantum computers are very detrimental to quantum computations. The ability to efficiently and accurately readout quantum states is crucial for quantum error correction schemes and quantum algorithms. Readout fidelity is typically limited by a poor signal-to-noise (SNR) ratio between the quantum states we intend to classify, as well as energy relaxation (e.g., T1T_1T1​ decay) from an excited state to a lower state during readout. Superconducting quantum bits (qubit), one of the leading candidates for scalable quantum computing hardware, are particularly limited by energy relaxation due to their relatively short coherence times. While most approaches for classifying the results of readout on superconducting qubits typically utilize clustering algorithms (e.g., a Gaussian mixture model) on integrated readout signals, these cannot distinguish between a quantum bit that was in the ground state prior to measurement from a qubit that decays to the ground state during measurement. For this reason, we instead propose using machine learning (ML) on the raw (non-integrated) analog signal and classification models on the full time series data (i.e., the \emph{trajectory}). We observe that time series classification methods, such as our chosen long short-term memory (LSTM) model, in combination with filtering and feature engineering techniques, consistently outperform clustering models. In particular, we find that the largest improvements come from reclassifying points in the boundary regions between neighboring clusters. These boundary points correspond to measurement records that deviate from the typical cluster, likely due to transient or noisy features in the signal that are not captured when the data is integrated. By retaining temporal information, sequence-aware models such as LSTMs can better discriminate these trajectories, whereas clustering methods based on integrated values are more prone to misclassifications.
Reliable qubit readout is a critical bottleneck toward fault-tolerant quantum computing (FTQC). In superconducting quantum processors, readout operations are both error-prone and high-latency. These challenges become more severe in frequency-multiplexed architectures, where signal crosstalk among neighboring qubits significantly degrades readout fidelity. Existing machine learning (ML)-based approaches rely on feed-forward neural networks (FNNs) that suffer from large parameter sizes and lack an end-to-end network that jointly addresses relaxation errors and discriminates qubit states. In this work, we present a multi-stage qubit state discriminator based on the Mamba model, which enables efficient sequence modeling with linear complexity. The first stage performs initial state discrimination, followed by a refinement stage that identifies and mitigates relaxation-induced errors. Our lightweight model achieves a geometric mean readout fidelity of 0.906, outperforming the best-reported state-of-the-art method while reducing parameter size by 49.6%; our optimal model further reaches 0.911. Both models remain robust across varying input trace lengths, maintaining a high fidelity of 0.893 at readout durations as short as 500 nsnsns, achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).