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 International Conference on Smart Innovations in Systems, Infrastructure, Mechanical, Power, AI and Computing Technologies (SISIMPACT)

Using AI Models for Fault-Tolerance in Quantum Computing

Saravanan K, Divakar G, Kaaviya K, Keerthivasan G, Rahul K

Published Nov 28, 2025• 0 citations
Publisher

Abstract

Correlated noise significantly hampers qubit stability and computational precision in quantum computing. Traditional error mitigation techniques assume independent noise and fail to adapt dynamically to evolving error patterns. To address this, we propose an AI-driven noise reduction framework that employs a Recurrent Neural Network (RNN)-Transformer architecture, achieving 92.4% accuracy in real-time noise prediction. Integrated federated learning enables secure, cross-device adaptation while preserving user privacy. Additionally, Bayesian optimization and adaptive gate reconfiguration reduce logical error rates by$\mathbf{4 3 \%}$and improve gate fidelity by$\mathbf{3 5 \%}$, enhancing overall computational reliability. Using IBM Quantum Falcon hardware, the proposed framework demonstrated superior stability and noise suppression compared to conventional methods. Through simulation and partial hardware validation, the reinforcement learning (RL) component effectively adapted error-correction strategies under varying noise conditions, ensuring continuous optimization. The framework's scalability and hardware independence were further confirmed through successful deployment on IBM Qiskit and Google Cirq, highlighting adaptability across heterogeneous quantum architectures. This study lays a robust foundation for advancing stable, accurate, and practical quantum computation.

DOI
10.1109/sisimpact67725.2025.11439155

Related papers

Enhancement of Machine Learning for Adaptive Quantum Computing Control: The Optimization Performance and Prevention of Real Time Error

V. Saravanan, Ganesan M, R. Balasubramaniyan +3 more

Adaptive quantum computing control is important for the stability and efficiency of quantum systems, especially in the presence of dynamic environmental noise and hardware fluctuations. We present a unified strategy for machine learning (ML) techniques to improve adaptive quantum control in two main directions: optimization speed and out-of-sample error. Here, we propose a hybrid learning method combining reinforcement learning (RL), deep neural networks (DNNs), and quantum-inspired models to actively and adaptively update quantum gate parameters and error mitigation strategies on the fly. Embedding of quantum noise models directly into the learning allows the system to predict and correct for decoherence, gate errors and measurement inaccuracy before they affect computational fidelity. Using extensive simulations as well as experimental validation on noisy intermediate-scale quantum (NISQ) processors, our improved ML model achieves a substantially higher fidelity and robustness compared to standard model-free and static control approaches. We introduce a novel feedback-loop mechanism based on online learning algorithms enabling the system to adjust for changing noise profiles and hardware drift without retraining. The optimization part uses metaheuristic methods to quickly converge to control parameters that perform well, and the error prevention mechanism features anomaly detection and prediction correction layers to minimize the effects of cumulative decoherence. The results demonstrate that our adaptive control framework can be used to not only speed up the convergence in training quantum algorithms, but also sustain the performance of gates against error at a variety of error rates with the reduction of the real-time impact of the error up to 35 %. This work highlights the promise of machine learningaugmented quantum control for improving reliability and scalability in quantum computing and serves as a stepping stone for future incorporation with fault-tolerant designs.

International Conference on Electronics and Computing, Communication Networking Automation Technologies (ICEC2NT)•Sep 3, 2025•3 citations

Quantum Machine Learning for Enhanced Qubit Stability and Gate Efficiency: A Qiskit-based Framework

Sanjay Saroja Parameswaran, M A Rohit Surya, Geetha K +2 more

The Noisy Intermediate-Scale Quantum (NISQ) era shows its practical applications through quantum computing which encounters essential problems with qubit stability and gate fidelity. This research introduces a complete quantum machine learning framework which uses IBM’s Qiskit toolkit to optimize quantum hardware performance through its predictive optimization and adaptive error correction systems. The proposed framework is based on Long Short-Term Memory (LSTM) networks for coherence time prediction, the Variational Quantum Eigensolver (VQE) to optimize gate performance, and Quantum Neural Networks (QNN) for error classification. Experiments conducted on IBM Quantum systems achieved significant performance enhancements which included an 18% increase in T1 coherence times, a 19% improvement in T2 times, and a 23% decrease in CNOT gate error rates. The decoherence predictor achieves 94.2% accuracy in forecasting coherence decay 300 microseconds in advance, while the QNN error classifier attains 91.7% accuracy across four error categories. The findings demonstrate that machine learning serves as an effective method to integrate existing NISQ systems with fault-tolerant quantum architectures, addressing the impact on algorithm development and error mitigation.

International Conference on Secure Information Systems and Technologies (ICSIST)•Aug 1, 2026•0 citations

A Statistical Framework for Dynamically Adaptive Logical Qubit Architectures for Scalable Fault-Tolerant Quantum Computing

M. Chandra Naik, M. Srikanth

The theoretical impediments of quantum computing to the large-scale implementation are inherently noise, decoherence, and inefficiency of the current fault-tolerant schemes. Although quantum hardware and error detection methods have made great advancements, existing methods largely use fixed logic qubit simulations and fixed noise models, which are inefficient at responding to dynamically changing noise models and do not scale. To curb this shortcoming, there is a need to have a framework that incorporates flexibility, statistical intelligence, and system optimization. In this paper, a dynamically adaptive logic qubit architecture is proposed based on a statistical model that can be used to achieve fault-tolerant quantum computing on a scale. The framework makes use of probabilistic noise modeling, real-time feedback-based reconfiguration in the continuous optimization of logical qubit structures and error correction schemes. The proposed architecture reduces the error propagation and reduces resource overhead by adding statistical inference using adaptive control mechanisms. Large-scale simulation experiments show that the given approach can suppress logical errors up to 28 percent better and reduce qubit overhead by 35 percent in comparison to the traditional fault-tolerant models that are based on static models and fault-tolerance in different noise levels. Moreover, the framework has a stable performance when the size of the system is growing, which indicates its stability and scalability. These results put dynamically adaptive logical qubit architectures as a potentially fruitful direction towards real-world and scalable quantum computing, and can be used in optimization, secure communication, and modeling of complex systems.

•Oct 29, 2026•0 citations

A Hybrid Classical-Quantum Reinforcement Learning Agent for Real-Time Noise Suppression in Quantum Processors

Awad Wehbe, Abdel‐Mehsen Ahmad

The fragility of quantum states to environmental noise presents a fundamental challenge for scalable quantum computing. While static error correction and optimal control pulses offer some mitigation, they lack the adaptability to counter time-varying noise. This paper introduces the HardwareInformed, Quantum-Aware, Deep Recurrent Neural-network Agent${ }^{2}$(HI-QA-DRNA${ }^{2}$), a hybrid classical-quantum framework for the real-time suppression of noise in quantum gate operations. HI-QA-DRNA${ }^{2}$employs a classical deep reinforcement learning agent, built on a Gated Recurrent Unit (GRU)Transformer architecture, to process a temporal sequence of noise observations. The agent predicts corrective parameters that dynamically adjust a base control pulse, which is then executed on a simulated, hardware-aware quantum processor. Crucially, the agent is trained using a composite reward function based on quantum information-theoretic metrics-state fidelity, von Neumann entropy, and Quantum Fisher Information (QFI)-that incentivizes not just accuracy but also state purity and robustness. This work demonstrate a significant performance advantage over an optimized static gate. On a test set of time-varying noise trajectories, The agent achieves a 74.6 % improvement in state purity and a 268.7 % improvement in robustness (1/QFI), with a modest 0.8 % gain in state fidelity. This multi-metric improvement underscores the value of the proposed holistic training framework for developing noise-resilient quantum control policies.

•Dec 14, 2025•0 citations

ENHANCING QUANTUM ERROR CORRECTION: OPTIMIZING NOISE REDUCTION TECHNIQUES FOR RELIABLE QUANTUM COMPUTATION

Ms. Priya D. Milke, Ms.Riya V. Shende, Ms.Rewati G. Patil +5 more

Quantum computing holds the potential to revolutionize computation by solving complex problems that classical computers cannot. However, quantum systems are highly susceptible to errors due to noise and decoherence. In this paper, we propose a novel hybrid AI-Quantum approach for Quantum Error Correction (QEC) to optimize noise reduction techniques. By leveraging deep learning and reinforcement learning, we develop a method to predict and correct quantum noise in real time. Our experiments, conducted on IBM Qiskit simulators and actual quantum processors, demonstrate a significant reduction in quantum gate errors compared to traditional QEC codes. Our method achieves improved fault tolerance with reduced qubit overhead, paving the way for scalable and reliable quantum computation. Furthermore, we make our research publicly available with open-source Python code and an interactive Jupyter notebook, enabling others to replicate and extend our work.

International Journal of Advance Scientific Research and Engineering Trends•Aug 14, 2024•0 citations

QAdapt: A Noise-Adaptive Neural Pre-Decoding Framework for Quantum Error Correction

Ran Miao, Rui Luo, Xiaohan Shan +1 more

Fault-tolerant quantum computing (FTQC) relies on quantum error correction to suppress physical errors and preserve logical information at scale. In practice, however, performance is constrained not only by physical noise but also by the latency of classical decoders processing rapidly generated syndrome data. This challenge is exacerbated by hardware noise that is strong, heterogeneous, and nonstationary, as well as by the simulation-to-hardware distribution shift that can substantially degrade fixed neural decoders. We present QAdapt, a noise-adaptive neural pre-decoding framework for surface-code quantum error correction. QAdapt captures local spatiotemporal correlations in syndrome data, sequentially adapts to evolving noise conditions while mitigating catastrophic forgetting, and forwards the residual syndrome to a conventional global decoder. Across 110 synthetic out-of-distribution noise configurations for rotated surface-code memory circuits, QAdapt consistently reduces the logical error rate relative to the neural pre-decoding baseline. On Google's Willow benchmark data, without target-domain fine-tuning, it achieves reductions of up to 5.79 percent in logical error rate and 9.32 percent in backend decoding latency on the residual syndrome. These results demonstrate that QAdapt provides a practical and decoder-compatible approach to improving the robustness and backend decoding efficiency of quantum error correction under evolving hardware noise.

cs.LGCross-listedarXiv:2607.28422•Jul 31, 2026•3 citations
Correlated noise significantly hampers qubit stability and computational precision in quantum computing. Traditional error mitigation techniques assume independent noise and fail to adapt dynamically to evolving error patterns. To address this, we propose an AI-driven noise reduction framework that employs a Recurrent Neural Network (RNN)-Transformer architecture, achieving 92.4% accuracy in real-time noise prediction. Integrated federated learning enables secure, cross-device adaptation while preserving user privacy. Additionally, Bayesian optimization and adaptive gate reconfiguration reduce logical error rates by43%\mathbf{4 3 \%}43%and improve gate fidelity by35%\mathbf{3 5 \%}35%, enhancing overall computational reliability. Using IBM Quantum Falcon hardware, the proposed framework demonstrated superior stability and noise suppression compared to conventional methods. Through simulation and partial hardware validation, the reinforcement learning (RL) component effectively adapted error-correction strategies under varying noise conditions, ensuring continuous optimization. The framework's scalability and hardware independence were further confirmed through successful deployment on IBM Qiskit and Google Cirq, highlighting adaptability across heterogeneous quantum architectures. This study lays a robust foundation for advancing stable, accurate, and practical quantum computation.
Adaptive quantum computing control is important for the stability and efficiency of quantum systems, especially in the presence of dynamic environmental noise and hardware fluctuations. We present a unified strategy for machine learning (ML) techniques to improve adaptive quantum control in two main directions: optimization speed and out-of-sample error. Here, we propose a hybrid learning method combining reinforcement learning (RL), deep neural networks (DNNs), and quantum-inspired models to actively and adaptively update quantum gate parameters and error mitigation strategies on the fly. Embedding of quantum noise models directly into the learning allows the system to predict and correct for decoherence, gate errors and measurement inaccuracy before they affect computational fidelity. Using extensive simulations as well as experimental validation on noisy intermediate-scale quantum (NISQ) processors, our improved ML model achieves a substantially higher fidelity and robustness compared to standard model-free and static control approaches. We introduce a novel feedback-loop mechanism based on online learning algorithms enabling the system to adjust for changing noise profiles and hardware drift without retraining. The optimization part uses metaheuristic methods to quickly converge to control parameters that perform well, and the error prevention mechanism features anomaly detection and prediction correction layers to minimize the effects of cumulative decoherence. The results demonstrate that our adaptive control framework can be used to not only speed up the convergence in training quantum algorithms, but also sustain the performance of gates against error at a variety of error rates with the reduction of the real-time impact of the error up to 35 %. This work highlights the promise of machine learningaugmented quantum control for improving reliability and scalability in quantum computing and serves as a stepping stone for future incorporation with fault-tolerant designs.
The Noisy Intermediate-Scale Quantum (NISQ) era shows its practical applications through quantum computing which encounters essential problems with qubit stability and gate fidelity. This research introduces a complete quantum machine learning framework which uses IBM’s Qiskit toolkit to optimize quantum hardware performance through its predictive optimization and adaptive error correction systems. The proposed framework is based on Long Short-Term Memory (LSTM) networks for coherence time prediction, the Variational Quantum Eigensolver (VQE) to optimize gate performance, and Quantum Neural Networks (QNN) for error classification. Experiments conducted on IBM Quantum systems achieved significant performance enhancements which included an 18% increase in T1 coherence times, a 19% improvement in T2 times, and a 23% decrease in CNOT gate error rates. The decoherence predictor achieves 94.2% accuracy in forecasting coherence decay 300 microseconds in advance, while the QNN error classifier attains 91.7% accuracy across four error categories. The findings demonstrate that machine learning serves as an effective method to integrate existing NISQ systems with fault-tolerant quantum architectures, addressing the impact on algorithm development and error mitigation.
The theoretical impediments of quantum computing to the large-scale implementation are inherently noise, decoherence, and inefficiency of the current fault-tolerant schemes. Although quantum hardware and error detection methods have made great advancements, existing methods largely use fixed logic qubit simulations and fixed noise models, which are inefficient at responding to dynamically changing noise models and do not scale. To curb this shortcoming, there is a need to have a framework that incorporates flexibility, statistical intelligence, and system optimization. In this paper, a dynamically adaptive logic qubit architecture is proposed based on a statistical model that can be used to achieve fault-tolerant quantum computing on a scale. The framework makes use of probabilistic noise modeling, real-time feedback-based reconfiguration in the continuous optimization of logical qubit structures and error correction schemes. The proposed architecture reduces the error propagation and reduces resource overhead by adding statistical inference using adaptive control mechanisms. Large-scale simulation experiments show that the given approach can suppress logical errors up to 28 percent better and reduce qubit overhead by 35 percent in comparison to the traditional fault-tolerant models that are based on static models and fault-tolerance in different noise levels. Moreover, the framework has a stable performance when the size of the system is growing, which indicates its stability and scalability. These results put dynamically adaptive logical qubit architectures as a potentially fruitful direction towards real-world and scalable quantum computing, and can be used in optimization, secure communication, and modeling of complex systems.
The fragility of quantum states to environmental noise presents a fundamental challenge for scalable quantum computing. While static error correction and optimal control pulses offer some mitigation, they lack the adaptability to counter time-varying noise. This paper introduces the HardwareInformed, Quantum-Aware, Deep Recurrent Neural-network Agent2{ }^{2}2(HI-QA-DRNA2{ }^{2}2), a hybrid classical-quantum framework for the real-time suppression of noise in quantum gate operations. HI-QA-DRNA2{ }^{2}2employs a classical deep reinforcement learning agent, built on a Gated Recurrent Unit (GRU)Transformer architecture, to process a temporal sequence of noise observations. The agent predicts corrective parameters that dynamically adjust a base control pulse, which is then executed on a simulated, hardware-aware quantum processor. Crucially, the agent is trained using a composite reward function based on quantum information-theoretic metrics-state fidelity, von Neumann entropy, and Quantum Fisher Information (QFI)-that incentivizes not just accuracy but also state purity and robustness. This work demonstrate a significant performance advantage over an optimized static gate. On a test set of time-varying noise trajectories, The agent achieves a 74.6 % improvement in state purity and a 268.7 % improvement in robustness (1/QFI), with a modest 0.8 % gain in state fidelity. This multi-metric improvement underscores the value of the proposed holistic training framework for developing noise-resilient quantum control policies.
Quantum computing holds the potential to revolutionize computation by solving complex problems that classical computers cannot. However, quantum systems are highly susceptible to errors due to noise and decoherence. In this paper, we propose a novel hybrid AI-Quantum approach for Quantum Error Correction (QEC) to optimize noise reduction techniques. By leveraging deep learning and reinforcement learning, we develop a method to predict and correct quantum noise in real time. Our experiments, conducted on IBM Qiskit simulators and actual quantum processors, demonstrate a significant reduction in quantum gate errors compared to traditional QEC codes. Our method achieves improved fault tolerance with reduced qubit overhead, paving the way for scalable and reliable quantum computation. Furthermore, we make our research publicly available with open-source Python code and an interactive Jupyter notebook, enabling others to replicate and extend our work.
Fault-tolerant quantum computing (FTQC) relies on quantum error correction to suppress physical errors and preserve logical information at scale. In practice, however, performance is constrained not only by physical noise but also by the latency of classical decoders processing rapidly generated syndrome data. This challenge is exacerbated by hardware noise that is strong, heterogeneous, and nonstationary, as well as by the simulation-to-hardware distribution shift that can substantially degrade fixed neural decoders. We present QAdapt, a noise-adaptive neural pre-decoding framework for surface-code quantum error correction. QAdapt captures local spatiotemporal correlations in syndrome data, sequentially adapts to evolving noise conditions while mitigating catastrophic forgetting, and forwards the residual syndrome to a conventional global decoder. Across 110 synthetic out-of-distribution noise configurations for rotated surface-code memory circuits, QAdapt consistently reduces the logical error rate relative to the neural pre-decoding baseline. On Google's Willow benchmark data, without target-domain fine-tuning, it achieves reductions of up to 5.79 percent in logical error rate and 9.32 percent in backend decoding latency on the residual syndrome. These results demonstrate that QAdapt provides a practical and decoder-compatible approach to improving the robustness and backend decoding efficiency of quantum error correction under evolving hardware noise.