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:2303.01134 · Scientific Reports

Error mitigation in brainbox quantum autoencoders

Joséphine Pazem, Mohammad H. Ansari

Published Jan 17, 2025• 12 citations
arXivHTMLPDF

Abstract

Quantum hardware faces noise challenges that disrupt multiqubit entangled states. Quantum autoencoder circuits with a single qubit bottleneck have demonstrated the capability to correct errors in noisy entangled states. By introducing slightly more complex structures in the bottleneck, referred to as brainboxes, the denoising process can occure more quickly and efficiently in the presence of stronger noise channels. Selecting the most suitable brainbox for the bottleneck involves a trade-off between the intensity of noise on the hardware and training complexity. Finally, by analysing the Rényi entropy flow throughout the networks, we demonstrate that the localization of entanglement plays a central role in denoising through learning.

DOI
10.1038/s41598-024-84171-z

Related papers

Quantum Error Mitigation via Autoencoder Neural Networks

Xiao-Dao Lin, Hsi-Ming Chang, Jhih-Shih You +1 more

Quantum computing has gained significant attention in recent years, with numerous algorithms and applications under active development. Limited by the current quantum technology, quantum noise and readout error have become critical issues. Various methods have been proposed to address readout error through error mitigation techniques, typically involving post-processing of measurement data. However, most of these methods increase the quantum hardware overhead, leading to higher computational costs. In this work, we present a machine-learning-based approach that minimizes hardware overhead while improving accuracy of the measurement probability distributions. We employed a convolutional neural network (CNN) autoencoder, commonly used for image denoising, as our baseline model. The datasets were derived from 4-qubit random circuits with depths ranging from 1 to 18, generated using Qiskit backends for target and noisy measurement data. The model was trained using mean squared error (MSE) as the loss function and Adam optimizer over 500 epochs, achieving an average noise reduction by 95% across the validation set, with no signs of overfitting. To validate the model's effectiveness across diverse quantum states, we conducted extensive tests on both typical quantum circuits and algorithms, including Grover's search algorithm, Quantum Fourier Transform, Haar random circuits and Trivial Paramagnet. The results demonstrated consistent and robust denoising in noisy measurement data, indicating that the autoencoder model is well-suited for efficient quantum error mitigation for current noisy quantum computers. This work contributes to the advancement of quantum error mitigation techniques using machine learning.

IEEE International Conference on Quantum Control, Computing and Learning (qCCL)•Jun 25, 2025•1 citation

Quantum Error Correction with Quantum Autoencoders

David F. Locher, Lorenzo Cardarelli, Markus Müller

Active quantum error correction is a central ingredient to achieve robust quantum processors. In this paper we investigate the potential of quantum machine learning for quantum error correction in a quantum memory. Specifically, we demonstrate how quantum neural networks, in the form of quantum autoencoders, can be trained to learn optimal strategies for active detection and correction of errors, including spatially correlated computational errors as well as qubit losses. We highlight that the denoising capabilities of quantum autoencoders are not limited to the protection of specific states but extend to the entire logical codespace. We also show that quantum neural networks can be used to discover new logical encodings that are optimally adapted to the underlying noise. Moreover, we find that, even in the presence of moderate noise in the quantum autoencoders themselves, they may still be successfully used to perform beneficial quantum error correction and thereby extend the lifetime of a logical qubit.

arXiv:2202.00555•Quantum•Mar 9, 2023•47 citations

Quantum Autoencoders to Denoise Quantum Data

Dmytro Bondarenko, Polina Feldmann

Entangled states are an important resource for quantum computation, communication, metrology, and the simulation of many-body systems. However, noise limits the experimental preparation of such states. Classical data can be efficiently denoised by autoencoders-neural networks trained in unsupervised manner. We develop a novel quantum autoencoder that successfully denoises Greenberger-Horne-Zeilinger, W, Dicke, and cluster states subject to spin-flip errors and random unitary noise. Various emergent quantum technologies could benefit from the proposed unsupervised quantum neural networks.

arXiv:1910.09169•Physical Review Letters•Mar 31, 2020•124 citations

Denoising quantum states with Quantum Autoencoders -- Theory and Applications

Tom Achache, Lior Horesh C, John A. Smolin

We implement a Quantum Autoencoder (QAE) as a quantum circuit capable of correcting Greenberger-Horne-Zeilinger (GHZ) states subject to various noisy quantum channels : the bit-flip channel and the more general quantum depolarizing channel. The QAE shows particularly interesting results, as it enables to perform an almost perfect reconstruction of noisy states, but can also, more surprisingly, act as a generative model to create noise-free GHZ states. Finally, we detail a useful application of QAEs : Quantum Secret Sharing (QSS). We analyze how noise corrupts QSS, causing it to fail, and show how the QAE allows the QSS protocol to succeed even in the presence of noise.

arXiv:2012.14714•Dec 29, 2020•28 citations

Noisy intermediate-scale quantum computer–compatible error correction of quantum data using modified dissipative quantum neural networks

Armin Ahmadkhaniha, M. Bathaee

Using a dissipative quantum neural network (DQNN) accompanied by conjugate layers, we upgrade the performance of the existing quantum autoencoder (QAE) network as a quantum denoiser of a noisy $m$-qubit GHZ state. Our denoising architecture requires a much smaller number of learning parameters, which can decrease the training time, especially when a deep or stacked DQNN is needed to approach the highest fidelity in the noisy intermediate-scale quantum era. In QAE, we reduce the connection between the hidden layer's qubits and the output's qubits to modify the decoder. The Renyi entropy of the hidden and output qubits' states is analyzed with respect to other qubits during learning iterations. During the learning process, if the hidden layer remains connected to the input layers, the network can almost perfectly denoise unseen noisy data with a different underlying noise distribution using the learning parameters acquired from training data.

arXiv:2311.10467•Physical Review A•Mar 25, 2024•1 citation

Generic detection-based error mitigation using quantum autoencoders

Xiao‐Ming Zhang, Weicheng Kong, Muhammad Usman Farooq +3 more

Efficient error-mitigation techniques demanding minimal resources is key to quantum information processing. We propose a generic protocol to mitigate quantum errors using detection-based quantum autoencoders. In our protocol, the quantum data are compressed into a latent subspace while leaving errors outside, the latter of which is then removed by a measurement and postselection. Compared to previously developed methods, our protocol on the one hand requires no extra qubits, and on the other hand it has a near-optimal denoising power, in which under reasonable requirements all errors detected outside of the latent subspace can be removed, while those inside the subspace cannot be removed by any means. Our detection-based quantum autoencoders are therefore particularly useful for near-term quantum devices in which controllable qubits are limited while noise reduction is important.

arXiv:2005.04341•Physical Review A•Apr 22, 2021•25 citations
Quantum hardware faces noise challenges that disrupt multiqubit entangled states. Quantum autoencoder circuits with a single qubit bottleneck have demonstrated the capability to correct errors in noisy entangled states. By introducing slightly more complex structures in the bottleneck, referred to as brainboxes, the denoising process can occure more quickly and efficiently in the presence of stronger noise channels. Selecting the most suitable brainbox for the bottleneck involves a trade-off between the intensity of noise on the hardware and training complexity. Finally, by analysing the Rényi entropy flow throughout the networks, we demonstrate that the localization of entanglement plays a central role in denoising through learning.
Quantum computing has gained significant attention in recent years, with numerous algorithms and applications under active development. Limited by the current quantum technology, quantum noise and readout error have become critical issues. Various methods have been proposed to address readout error through error mitigation techniques, typically involving post-processing of measurement data. However, most of these methods increase the quantum hardware overhead, leading to higher computational costs. In this work, we present a machine-learning-based approach that minimizes hardware overhead while improving accuracy of the measurement probability distributions. We employed a convolutional neural network (CNN) autoencoder, commonly used for image denoising, as our baseline model. The datasets were derived from 4-qubit random circuits with depths ranging from 1 to 18, generated using Qiskit backends for target and noisy measurement data. The model was trained using mean squared error (MSE) as the loss function and Adam optimizer over 500 epochs, achieving an average noise reduction by 95% across the validation set, with no signs of overfitting. To validate the model's effectiveness across diverse quantum states, we conducted extensive tests on both typical quantum circuits and algorithms, including Grover's search algorithm, Quantum Fourier Transform, Haar random circuits and Trivial Paramagnet. The results demonstrated consistent and robust denoising in noisy measurement data, indicating that the autoencoder model is well-suited for efficient quantum error mitigation for current noisy quantum computers. This work contributes to the advancement of quantum error mitigation techniques using machine learning.
Active quantum error correction is a central ingredient to achieve robust quantum processors. In this paper we investigate the potential of quantum machine learning for quantum error correction in a quantum memory. Specifically, we demonstrate how quantum neural networks, in the form of quantum autoencoders, can be trained to learn optimal strategies for active detection and correction of errors, including spatially correlated computational errors as well as qubit losses. We highlight that the denoising capabilities of quantum autoencoders are not limited to the protection of specific states but extend to the entire logical codespace. We also show that quantum neural networks can be used to discover new logical encodings that are optimally adapted to the underlying noise. Moreover, we find that, even in the presence of moderate noise in the quantum autoencoders themselves, they may still be successfully used to perform beneficial quantum error correction and thereby extend the lifetime of a logical qubit.
Entangled states are an important resource for quantum computation, communication, metrology, and the simulation of many-body systems. However, noise limits the experimental preparation of such states. Classical data can be efficiently denoised by autoencoders-neural networks trained in unsupervised manner. We develop a novel quantum autoencoder that successfully denoises Greenberger-Horne-Zeilinger, W, Dicke, and cluster states subject to spin-flip errors and random unitary noise. Various emergent quantum technologies could benefit from the proposed unsupervised quantum neural networks.
We implement a Quantum Autoencoder (QAE) as a quantum circuit capable of correcting Greenberger-Horne-Zeilinger (GHZ) states subject to various noisy quantum channels : the bit-flip channel and the more general quantum depolarizing channel. The QAE shows particularly interesting results, as it enables to perform an almost perfect reconstruction of noisy states, but can also, more surprisingly, act as a generative model to create noise-free GHZ states. Finally, we detail a useful application of QAEs : Quantum Secret Sharing (QSS). We analyze how noise corrupts QSS, causing it to fail, and show how the QAE allows the QSS protocol to succeed even in the presence of noise.
Using a dissipative quantum neural network (DQNN) accompanied by conjugate layers, we upgrade the performance of the existing quantum autoencoder (QAE) network as a quantum denoiser of a noisy mmm-qubit GHZ state. Our denoising architecture requires a much smaller number of learning parameters, which can decrease the training time, especially when a deep or stacked DQNN is needed to approach the highest fidelity in the noisy intermediate-scale quantum era. In QAE, we reduce the connection between the hidden layer's qubits and the output's qubits to modify the decoder. The Renyi entropy of the hidden and output qubits' states is analyzed with respect to other qubits during learning iterations. During the learning process, if the hidden layer remains connected to the input layers, the network can almost perfectly denoise unseen noisy data with a different underlying noise distribution using the learning parameters acquired from training data.
Efficient error-mitigation techniques demanding minimal resources is key to quantum information processing. We propose a generic protocol to mitigate quantum errors using detection-based quantum autoencoders. In our protocol, the quantum data are compressed into a latent subspace while leaving errors outside, the latter of which is then removed by a measurement and postselection. Compared to previously developed methods, our protocol on the one hand requires no extra qubits, and on the other hand it has a near-optimal denoising power, in which under reasonable requirements all errors detected outside of the latent subspace can be removed, while those inside the subspace cannot be removed by any means. Our detection-based quantum autoencoders are therefore particularly useful for near-term quantum devices in which controllable qubits are limited while noise reduction is important.