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:2311.12217 · Physical Review Applied

Enhanced measurement of neutral-atom qubits with machine learning

Linipun Phuttitarn, B. M. Becker, Ravikumar Chinnarasu, T. M. Graham, Mark E. Saffman

Published Aug 5, 2024• 12 citations
arXivHTMLPDF

Abstract

We demonstrate qubit-state measurements assisted by a supervised convolutional neural network (CNN) in a neutral-atom quantum processor. We present two CNN architectures for analyzing neutral-atom qubit readout data: a compact five-layer single-qubit CNN architecture and a six-layer multiqubit CNN architecture. We benchmark both architectures against a conventional Gaussian-threshold analysis method. In a sparse array (9-$\text{\ensuremath{\mu}}\mathrm{m}$ atom separation) which experiences negligible crosstalk, we have observed up to 32% and 56% error reduction for the multiqubit and single-qubit architectures, respectively, as compared to the benchmark. In a tightly spaced array (5-$\text{\ensuremath{\mu}}\mathrm{m}$ atom separation), which suffers from readout crosstalk, we have observed up to 43% and 32% error reduction in the multiqubit and single-qubit CNN architectures, respectively, as compared to the benchmark. By examining the correlation between the predicted states of neighboring qubits, we have found that the multiqubit CNN architecture reduces the crosstalk correlation by up to 78.5%. This work demonstrates a proof of concept for a CNN network to be implemented as a real-time readout-processing method on a neutral-atom quantum computer, enabling faster readout time and improved fidelity.

DOI
10.1103/physrevapplied.22.024011

Related papers

Efficient measurement of neutral-atom qubits with matched filters

Robert M. Kent, Linipun Phuttitarn, Chaithanya Naik Mude +4 more

Quantum computers require high-fidelity measurement of many qubits to achieve a quantum advantage. Traditional approaches suffer from readout crosstalk for a neutral-atom quantum processor with a tightly spaced array. Although classical machine learning algorithms based on convolutional neural networks can improve fidelity, they are computationally expensive, making it difficult to scale them to large qubit counts. We present two simpler and scalable machine learning algorithms that realize matched filters for the readout problem. One is a local model that focuses on a single qubit, and the other uses information from neighboring qubits in the array to prevent crosstalk among the qubits. We demonstrate error reductions of up to 32% and 43% for the site and array models, respectively, compared to a conventional Gaussian threshold approach. Additionally, our array model uses two orders of magnitude fewer trainable parameters and four orders of magnitude fewer multiplications and nonlinear function evaluations than a recent convolutional neural network approach, with only a minor (3.5%) increase in error across different readout times. Another strength of our approach is its physical interpretability: the learned filter can be visualized to provide insights into experimental imperfections. We also show that a convolutional neural network model for improved can be pruned to have 70x and 4000x fewer parameters, respectively, while maintaining similar errors. Our work shows that simple machine learning approaches can achieve high-fidelity qubit measurements while remaining scalable to systems with larger qubit counts.

arXiv:2504.08170•Physical Review Applied•Feb 17, 2026•1 citation

Machine learning assisted readout of trapped-ion qubits

Alireza Seif, Kevin A Landsman, Norbert M. Linke +3 more

Abstract We reduce measurement errors in a quantum computer using machine learning techniques. We exploit a simple yet versatile neural network to classify multi-qubit quantum states, which is trained using experimental data. This flexible approach allows the incorporation of any number of features of the data with minimal modifications to the underlying network architecture. We experimentally illustrate this approach in the readout of trapped-ion qubits using additional spatial and temporal features in the data. Using this neural network classifier, we efficiently treat qubit readout crosstalk, resulting in a 30% improvement in detection error over the conventional threshold method. Our approach does not depend on the specific details of the system and can be readily generalized to other quantum computing platforms.

arXiv:1804.07718•Journal of Physics B Atomic Molecular and Optical Physics•Jul 26, 2018•52 citations

AI-Accelerated Qubit Readout at the Single-Photon Level for Scalable Atomic Quantum Processors

Yaoting Zhou, Weisen Wang, Zhuangzhuang Tian +6 more

Quantum state readout with minimal resources is crucial for scalable quantum information processing. As a leading platform, neutral atom arrays rely on atomic fluorescence imaging for qubit readout, requiring short exposure, low photon count schemes to mitigate heating and atom loss while enabling mid-circuit feedback. However, a fundamental challenge arises in the single-photon regime where severe overlap in state distributions causes conventional threshold discrimination to fail. Here, we report an AI-accelerated Bayesian inference method for fluorescence readout in neutral atom arrays. Our approach leverages Bayesian inference to achieve reliable state detection at the single-photon level under short exposure. Specifically, we introduce a weakly anchored Bayesian scheme that requires calibration of only one state, addressing asymmetric calibration challenges common across quantum platforms. Furthermore, acceleration is achieved via a permutation-invariant neural network, which yields a 100-fold speedup by compressing iterative inference into a single forward pass. The approach achieves relative readout fidelity above 99% and 98% for histogram overlaps of 61% and 72%, respectively, enabling reliable extraction of Rabi oscillations and Ramsey interference results unattainable with conventional threshold based methods. This framework supports scalable, real-time readout of large atom arrays and paves the way toward AI-enhanced quantum technology in computation and sensing.

quant-pharXiv:2512.20919•Dec 25, 2025•0 citations

Mitigating Crosstalk-Induced Qubit Readout Error with Shallow-Neural-Network Discrimination

Peng Duan, Zifeng Chen, Qi Zhou +3 more

Measurement of qubits plays a key role in quantum computation. In superconducting multiqubit quantum processors, a multiplexed readout scheme is widely used. In such a scheme, measurement of a qubit state may be influenced by the state of neighboring qubits, due to various crosstalk effects, which will degrade the readout fidelity. To reduce the impact of crosstalk, we model the digital signal processing system used in measurements as a shallow neural network and train it to become a state discriminator. Applying our method to a six-qubit superconducting quantum chip, we see an overall improved readout performance compared with a contemporary qubit-state discriminator. The readout crosstalk is decreased by more than $80\mathrm{%}$. The training and optimization process of the neural network consumes only about 10 s.

Physical Review Applied•Aug 31, 2021•18 citations

Machine Learning-Enhanced Entanglement Characterization in Bi-partite Ququart Systems

Rithvik Sreekantham, Ravindra Pratap Singh, Shashi Prabhakar

Abstract We present a systematic comparative analysis of machine learning and traditional approaches for quantum entanglement characterization in bi-partite ququart systems. Quantifying entanglement traditionally requires full quantum state tomography, necessitating $N_{mub}^2D^2N_{cop}$ measurements, where $N_{mub}$ is the number of mutually unbiased bases, $D$ is the subsystem dimensionality, and $N_{cop}$ is the number of identical copies. For ququart systems with $D=4$, this translates to hundreds of distinct measurement settings, each requiring multiple copies ($N_{cop}$ typically in thousands)—resulting in hundreds of thousands of total measurements in practice. Our research demonstrates that neural networks achieve comparable or superior accuracy with orders of magnitude fewer measurement settings. We evaluate three architectures—Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Transformer—against Maximum Likelihood Estimation (MLE) and Bayesian methods across measurement counts ranging from 10 to 400. Neural approaches achieve up to 1650× faster computation times compared to traditional methods while maintaining competitive accuracy. At 100 measurements, the Transformer achieves Mean Squared Error (MSE) of $1.49 \times 10^{-1}$, while MLE yields $2.04 \times 10^{-1}$—over 10× higher error—despite taking 178 times longer. All neural methods in our study show error reduction scaling as approximately $1/\sqrt{N}$ with increased measurements. While this observed scaling might be influenced by our specific architectures, it provides important practical guidance for experimental design. The Transformer architecture demonstrates exceptional sample efficiency, achieving with 100 measurements what traditional methods require 250-400 measurements to accomplish—a significant advantage for resource-constrained quantum experiments. This research provides a viable pathway for real-time entanglement characterization in higher-dimensional quantum systems where traditional methods become computationally prohibitive.

•Jun 10, 2025•0 citations

Superconducting-qubit readout using next-generation reservoir computing

Robert Kent, Benjamin Lienhard, Gregory P. Lafyatis +1 more

Quantum processors require rapid and high-fidelity simultaneous measurements of many qubits. While superconducting qubits are among the leading modalities toward a useful quantum processor, their readout remains a bottleneck. Traditional approaches to processing measurement data often struggle to account for crosstalk present in frequency-multiplexed readout, the preferred method to reduce the resource overhead. Recent approaches to address this challenge use neural networks to improve the state-discrimination fidelity. However, they are computationally expensive to train and evaluate, resulting in increased latency and poor scalability as the number of qubits increases. We present an alternative machine learning approach based on next-generation reservoir computing that constructs polynomial features from the measurement signals and maps them to the corresponding qubit states. This method is highly parallelizable, avoids the costly nonlinear activation functions common in neural networks, and supports real-time training, enabling fast evaluation, adaptability, and scalability. Despite its lower computational complexity, our reservoir approach is able to maintain high qubit-state-discrimination fidelity. Relative to traditional methods, our approach achieves error reductions of up to 50% and 11% on single- and five-qubit datasets, respectively, and delivers up to 2.5x crosstalk reduction on the five-qubit dataset. Compared with recent machine-learning methods, evaluating our model requires 100x fewer multiplications for single-qubit and 2.5x fewer for five-qubit models. This work demonstrates that reservoir computing can enhance qubit-state discrimination while maintaining scalability for future quantum processors.

arXiv:2506.15771•Physical Review Applied•Mar 2, 2026•2 citations
We demonstrate qubit-state measurements assisted by a supervised convolutional neural network (CNN) in a neutral-atom quantum processor. We present two CNN architectures for analyzing neutral-atom qubit readout data: a compact five-layer single-qubit CNN architecture and a six-layer multiqubit CNN architecture. We benchmark both architectures against a conventional Gaussian-threshold analysis method. In a sparse array (9-\ensuremath\mum\text{\ensuremath{\mu}}\mathrm{m}\ensuremath\mum atom separation) which experiences negligible crosstalk, we have observed up to 32% and 56% error reduction for the multiqubit and single-qubit architectures, respectively, as compared to the benchmark. In a tightly spaced array (5-\ensuremath\mum\text{\ensuremath{\mu}}\mathrm{m}\ensuremath\mum atom separation), which suffers from readout crosstalk, we have observed up to 43% and 32% error reduction in the multiqubit and single-qubit CNN architectures, respectively, as compared to the benchmark. By examining the correlation between the predicted states of neighboring qubits, we have found that the multiqubit CNN architecture reduces the crosstalk correlation by up to 78.5%. This work demonstrates a proof of concept for a CNN network to be implemented as a real-time readout-processing method on a neutral-atom quantum computer, enabling faster readout time and improved fidelity.
Quantum computers require high-fidelity measurement of many qubits to achieve a quantum advantage. Traditional approaches suffer from readout crosstalk for a neutral-atom quantum processor with a tightly spaced array. Although classical machine learning algorithms based on convolutional neural networks can improve fidelity, they are computationally expensive, making it difficult to scale them to large qubit counts. We present two simpler and scalable machine learning algorithms that realize matched filters for the readout problem. One is a local model that focuses on a single qubit, and the other uses information from neighboring qubits in the array to prevent crosstalk among the qubits. We demonstrate error reductions of up to 32% and 43% for the site and array models, respectively, compared to a conventional Gaussian threshold approach. Additionally, our array model uses two orders of magnitude fewer trainable parameters and four orders of magnitude fewer multiplications and nonlinear function evaluations than a recent convolutional neural network approach, with only a minor (3.5%) increase in error across different readout times. Another strength of our approach is its physical interpretability: the learned filter can be visualized to provide insights into experimental imperfections. We also show that a convolutional neural network model for improved can be pruned to have 70x and 4000x fewer parameters, respectively, while maintaining similar errors. Our work shows that simple machine learning approaches can achieve high-fidelity qubit measurements while remaining scalable to systems with larger qubit counts.
Abstract We reduce measurement errors in a quantum computer using machine learning techniques. We exploit a simple yet versatile neural network to classify multi-qubit quantum states, which is trained using experimental data. This flexible approach allows the incorporation of any number of features of the data with minimal modifications to the underlying network architecture. We experimentally illustrate this approach in the readout of trapped-ion qubits using additional spatial and temporal features in the data. Using this neural network classifier, we efficiently treat qubit readout crosstalk, resulting in a 30% improvement in detection error over the conventional threshold method. Our approach does not depend on the specific details of the system and can be readily generalized to other quantum computing platforms.
Quantum state readout with minimal resources is crucial for scalable quantum information processing. As a leading platform, neutral atom arrays rely on atomic fluorescence imaging for qubit readout, requiring short exposure, low photon count schemes to mitigate heating and atom loss while enabling mid-circuit feedback. However, a fundamental challenge arises in the single-photon regime where severe overlap in state distributions causes conventional threshold discrimination to fail. Here, we report an AI-accelerated Bayesian inference method for fluorescence readout in neutral atom arrays. Our approach leverages Bayesian inference to achieve reliable state detection at the single-photon level under short exposure. Specifically, we introduce a weakly anchored Bayesian scheme that requires calibration of only one state, addressing asymmetric calibration challenges common across quantum platforms. Furthermore, acceleration is achieved via a permutation-invariant neural network, which yields a 100-fold speedup by compressing iterative inference into a single forward pass. The approach achieves relative readout fidelity above 99% and 98% for histogram overlaps of 61% and 72%, respectively, enabling reliable extraction of Rabi oscillations and Ramsey interference results unattainable with conventional threshold based methods. This framework supports scalable, real-time readout of large atom arrays and paves the way toward AI-enhanced quantum technology in computation and sensing.
Measurement of qubits plays a key role in quantum computation. In superconducting multiqubit quantum processors, a multiplexed readout scheme is widely used. In such a scheme, measurement of a qubit state may be influenced by the state of neighboring qubits, due to various crosstalk effects, which will degrade the readout fidelity. To reduce the impact of crosstalk, we model the digital signal processing system used in measurements as a shallow neural network and train it to become a state discriminator. Applying our method to a six-qubit superconducting quantum chip, we see an overall improved readout performance compared with a contemporary qubit-state discriminator. The readout crosstalk is decreased by more than $80\mathrm{%}$. The training and optimization process of the neural network consumes only about 10 s.
Abstract We present a systematic comparative analysis of machine learning and traditional approaches for quantum entanglement characterization in bi-partite ququart systems. Quantifying entanglement traditionally requires full quantum state tomography, necessitating Nmub2D2NcopN_{mub}^2D^2N_{cop}Nmub2​D2Ncop​ measurements, where NmubN_{mub}Nmub​ is the number of mutually unbiased bases, DDD is the subsystem dimensionality, and NcopN_{cop}Ncop​ is the number of identical copies. For ququart systems with D=4D=4D=4, this translates to hundreds of distinct measurement settings, each requiring multiple copies (NcopN_{cop}Ncop​ typically in thousands)—resulting in hundreds of thousands of total measurements in practice. Our research demonstrates that neural networks achieve comparable or superior accuracy with orders of magnitude fewer measurement settings. We evaluate three architectures—Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Transformer—against Maximum Likelihood Estimation (MLE) and Bayesian methods across measurement counts ranging from 10 to 400. Neural approaches achieve up to 1650× faster computation times compared to traditional methods while maintaining competitive accuracy. At 100 measurements, the Transformer achieves Mean Squared Error (MSE) of 1.49×10−11.49 \times 10^{-1}1.49×10−1, while MLE yields 2.04×10−12.04 \times 10^{-1}2.04×10−1—over 10× higher error—despite taking 178 times longer. All neural methods in our study show error reduction scaling as approximately 1/N1/\sqrt{N}1/N​ with increased measurements. While this observed scaling might be influenced by our specific architectures, it provides important practical guidance for experimental design. The Transformer architecture demonstrates exceptional sample efficiency, achieving with 100 measurements what traditional methods require 250-400 measurements to accomplish—a significant advantage for resource-constrained quantum experiments. This research provides a viable pathway for real-time entanglement characterization in higher-dimensional quantum systems where traditional methods become computationally prohibitive.
Quantum processors require rapid and high-fidelity simultaneous measurements of many qubits. While superconducting qubits are among the leading modalities toward a useful quantum processor, their readout remains a bottleneck. Traditional approaches to processing measurement data often struggle to account for crosstalk present in frequency-multiplexed readout, the preferred method to reduce the resource overhead. Recent approaches to address this challenge use neural networks to improve the state-discrimination fidelity. However, they are computationally expensive to train and evaluate, resulting in increased latency and poor scalability as the number of qubits increases. We present an alternative machine learning approach based on next-generation reservoir computing that constructs polynomial features from the measurement signals and maps them to the corresponding qubit states. This method is highly parallelizable, avoids the costly nonlinear activation functions common in neural networks, and supports real-time training, enabling fast evaluation, adaptability, and scalability. Despite its lower computational complexity, our reservoir approach is able to maintain high qubit-state-discrimination fidelity. Relative to traditional methods, our approach achieves error reductions of up to 50% and 11% on single- and five-qubit datasets, respectively, and delivers up to 2.5x crosstalk reduction on the five-qubit dataset. Compared with recent machine-learning methods, evaluating our model requires 100x fewer multiplications for single-qubit and 2.5x fewer for five-qubit models. This work demonstrates that reservoir computing can enhance qubit-state discrimination while maintaining scalability for future quantum processors.