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

The Open Bioinformatics Journal

Balancing Accuracy and Recall in Hebbian and Quantum-Inspired Learning Models

Theodoros A. Kyriazos, Mary Poga

Published Apr 25, 2025• 2 citations
Publisher

Abstract

Introduction This study investigates integrating quantum-inspired learning models with traditional Hebbian learning within neural networks, comparing their performance in learning efficiency, generalization, stability, and robustness. Traditional Hebbian models are biologically plausible but often struggle with stability, scalability, and adaptability. In contrast, quantum-inspired models leverage quantum mechanics principles like superposition and entanglement to enhance neural network performance potentially. Methods The simulations were conducted using a neural network comprising 1,000 neurons and 100 patterns across 10 instances. The key parameters included a fixed decay rate of 0.005, 80% excitatory neurons, and 10% fixed connectivity. The study varied learning rates (0.01, 0.05, 0.1) and thresholds (0.3, 0.5, 0.7) to assess different parameter settings. The performance metrics evaluated included accuracy, precision, recall, and F1-Score. Results The results showed that quantum-inspired models achieved significantly higher accuracy and precision, enhancing their reliability in class prediction and reducing false positives. Conversely, Hebbian models excelled in recall and F1-Score, effectively identifying positive cases and balancing precision and recall. Additionally, quantum-inspired models demonstrated greater stability, robustness, and consistent performance across varying parameters. Conclusion Quantum-inspired models offer notable improvements in learning efficiency, generalization, stability, and robustness, while Hebbian models perform better in recall and F1-Score. These findings suggest the potential for hybrid models that combine the strengths of both approaches, aiming for more balanced and efficient learning systems. Future research should explore these hybrid models to enhance performance across diverse artificial intelligence applications. Supplementary materials include the complete R code used, enabling replication and further investigation of the results.

DOI
10.2174/0118750362380098250416071630

Related papers

Quantum deep neural networks modeling for inventory management

Sarit Maitra

Purpose The purpose of this study is to explore the potential for quantum computing to enhance applied machine learning tasks. The goal is to investigate whether quantum computing principles such as superposition, entanglement and quantum parallelism can improve predictive accuracy and efficiency in machine learning models. Design/methodology/approach To examine the potential, this study simulated a 4-qubit quantum processor on an Intel Core i5 8th generation central processing unit (CPU). The proposed model combines quantum principle and deep neural networks architecture involving quantum-forward and classical-backward processes; quantum part is in the forward pass, and the traditional neural network handles the backpropagation during model training. This model was tested using a real dataset to assess its practical applicability to machine learning tasks under real-world constraints. Findings The findings reveal the effectiveness of the quantum-classical hybrid approach which achieves an average area under the curve score of 92%, with a precision of 22.6% and a recall of 25.3%. These results suggest that, while quantum noise and Qubit limitations inherent to Noisy Intermediate-Scale Quantum systems impacted prediction accuracy and model generalizability, the quantum-forward process enhanced the model’s ability to identify true positive cases in a complex dataset. Compared to traditional approaches, this model addresses both the stability and predictive demands of highly imbalanced inventory data, although limitations remain in precision and scalability. Originality/value While many open questions remain about the real advantages of quantum computing in applied field of business, this study contributes to the feasibility of leveraging quantum machine learning for complex decision-making problems in supply chain management.

Journal of Modelling in Management•Dec 18, 2025•0 citations

Quantum Neural Networks with Bio-Inspired Adaptive Learning

Jincheng Zhang

This paper proposes a novel architecture for quantum neural networks (QNNs) inspired by biological neural networks, specifically focusing on adaptive learning capabilities. The core idea is to integrate biological mechanisms such as synaptic plasticity and long-range dependencies into the quantum learning process. The traditional approach to QNN training often relies on gradient-based methods, which can be inefficient and susceptible to local minima. This work introduces a bio-inspired approach that leverages the inherent parallelism and quantum superposition of QNNs to achieve more robust and adaptive learning. We formulate the learning process using a modified Hebbian learning rule combined with a quantum measurement process. The key innovation lies in dynamically adjusting the quantum gates based on the network's internal state, mimicking the neural network's ability to adapt to changing environments. The resulting QNN architecture exhibits enhanced learning speed and improved generalization performance compared to conventional QNNs. The theoretical framework is presented, and the underlying mathematical equations are detailed, providing a robust foundation for further research and development in this field.

•Sep 5, 2026•0 citations

Quantum-Inspired Optimization for Neural Networks

Jincheng Zhang

Quantum-inspired optimization is a burgeoning field aiming to leverage the principles of quantum mechanics to enhance the efficiency of training neural networks. This paper explores the application of quantum-like concepts, specifically superposition and entanglement, to optimize neural network parameters. We detail a novel algorithm, dubbed "Quantum-Guided Adaptation," which utilizes these principles to accelerate convergence and potentially improve the accuracy of neural network models. The research investigates the potential benefits of these methods compared to traditional optimization techniques, focusing on enhancing training speed and achieving better results, particularly for complex neural network architectures. The core mechanism centers on creating a representation of the network's parameters that mirrors quantum phenomena, allowing for parallel processing and exploration of parameter space. We demonstrate the effectiveness of this approach through simulations and preliminary analysis, suggesting a significant improvement in training time and model accuracy.

•Aug 29, 2026•0 citations

Quantum inspired qubit qutrit neural networks for real time financial forecasting

Kanishk Bakshi, Kathiravan Srinivasan

This research investigates the performance and efficacy of machine learning models in stock prediction, comparing Artificial Neural Networks (ANNs), Quantum Qubit-based Neural Networks (QQBNs), and Quantum Qutrit-based Neural Networks (QQTNs). By outlining methodologies, architectures, and training procedures, the study highlights significant differences in training times and performance metrics across models. While all models demonstrate robust accuracies above 70%, the Quantum Qutrit-based Neural Network consistently outperforms with advantages in risk-adjusted returns, measured by the Sharpe ratio, greater consistency in prediction quality through the Information Coefficient, and enhanced robustness under varying market conditions. The QQTN not only surpasses its classical and qubit-based counterparts in multiple quantitative and qualitative metrics but also achieves comparable performance with significantly reduced training times. These results showcase the promising prospects of Quantum Qutrit-based Neural Networks in practical financial applications, where real-time processing is critical. By achieving superior accuracy, efficiency, and adaptability, the proposed models underscore the transformative potential of quantum-inspired approaches, paving the way for their integration into computationally intensive fields.

cs.AICross-listedarXiv:2604.18838•Scientific Reports•Apr 22, 2026•8 citations

Comparing Classical Hopfield Networks and a Hybrid Quantum-Classical Associative Memory Model: Recall Accuracy, Noise Robustness, and Storage Capacity

Sanjay Shivaganesh

Associative memory, the ability to reconstruct complete information from partial or noisy cues, is a defining feature of human cognition and an enduring objective in artificial intelligence. Classical neural models such as Hopfield networks have long provided insight into distributed storage and retrieval mechanisms, yet they remain constrained by limited storage capacity and susceptibility to noise. Recent developments in quantum computing have motivated investigation of hybrid quantum-classical architectures as alternative approaches to memory representation and retrieval. This study examines how effectively hybrid quantum-classical models can reproduce associative memory functions compared to Hopfield networks, with a particular focus on recall accuracy under varying noise levels, storage capacity, and computational efficiency. Through small-scale experiments using binary patterns and hybrid quantum circuits, we evaluate potential quantum advantages and practical trade-offs. The findings contribute to ongoing discourse in quantum machine learning and cognitive modeling, underscoring both the promise and current limitations of quantum-inspired associative memory systems. Our guiding research question is: To what extent can hybrid quantum–classical models replicate associative memory functions more effectively than classical neural memory models, particularly in terms of recall accuracy under noise and storage capacity?

•Sep 14, 2026•0 citations

Quantum-Inspired Neural Network For Enhanced Image Recognition

Raj. TF Michael, G. Rmesh, Moorthy Agoramoorthy +2 more

The field of quantum computing has seen significant progress in recent times, leading to the emergence of innovative methodologies across several areas, particularly in machine learning and neural networks. This research study introduces a quantum-inspired neural network (QINN) that has been particularly developed to improve image recognition capabilities. In contrast to conventional neural networks, the Quantum-inspired Neural Network (QINN) utilizes concepts derived from quantum mechanics, including superposition and entanglement, to process and encode information effectively. The paradigm we propose incorporates quantum bits (qubits) as computing units instead of traditional binary nodes, simultaneously enabling the representation of many states. Moreover, the use of the intrinsic parallelism of quantum mechanics is harnessed to provide expedited and more effective data processing, particularly within the concealed levels of the network. The researchers ran benchmark tests using well-recognized image datasets, including CIFAR-10 and ImageNet. The study's findings indicated that QINN displayed superior accuracy rates compared to traditional methods and revealed faster convergence throughout the training process. Additionally, our quantum-inspired methodology demonstrated significant efficacy in analyzing pictures containing nuanced characteristics, highlighting its potential in practical scenarios where precise identification is of utmost importance. In summary, integrating quantum principles with neural network topologies has the potential for groundbreaking advancement in image recognition skills. QINN is a groundbreaking advancement in this domain, emphasizing the unexplored capacity to use quantum phenomena for sophisticated machine learning objectives. Potential areas for future study are the expansion of network scalability to accommodate bigger datasets, exploration of security measures that are resilient against quantum threats, and investigating hybrid models that integrate both quantum and conventional paradigms to enhance overall performance.

International Conference on Intelligent Computing and Control for Engineering and Business Systems (ICCEBS)•Dec 14, 2023•20 citations
Introduction This study investigates integrating quantum-inspired learning models with traditional Hebbian learning within neural networks, comparing their performance in learning efficiency, generalization, stability, and robustness. Traditional Hebbian models are biologically plausible but often struggle with stability, scalability, and adaptability. In contrast, quantum-inspired models leverage quantum mechanics principles like superposition and entanglement to enhance neural network performance potentially. Methods The simulations were conducted using a neural network comprising 1,000 neurons and 100 patterns across 10 instances. The key parameters included a fixed decay rate of 0.005, 80% excitatory neurons, and 10% fixed connectivity. The study varied learning rates (0.01, 0.05, 0.1) and thresholds (0.3, 0.5, 0.7) to assess different parameter settings. The performance metrics evaluated included accuracy, precision, recall, and F1-Score. Results The results showed that quantum-inspired models achieved significantly higher accuracy and precision, enhancing their reliability in class prediction and reducing false positives. Conversely, Hebbian models excelled in recall and F1-Score, effectively identifying positive cases and balancing precision and recall. Additionally, quantum-inspired models demonstrated greater stability, robustness, and consistent performance across varying parameters. Conclusion Quantum-inspired models offer notable improvements in learning efficiency, generalization, stability, and robustness, while Hebbian models perform better in recall and F1-Score. These findings suggest the potential for hybrid models that combine the strengths of both approaches, aiming for more balanced and efficient learning systems. Future research should explore these hybrid models to enhance performance across diverse artificial intelligence applications. Supplementary materials include the complete R code used, enabling replication and further investigation of the results.
Purpose The purpose of this study is to explore the potential for quantum computing to enhance applied machine learning tasks. The goal is to investigate whether quantum computing principles such as superposition, entanglement and quantum parallelism can improve predictive accuracy and efficiency in machine learning models. Design/methodology/approach To examine the potential, this study simulated a 4-qubit quantum processor on an Intel Core i5 8th generation central processing unit (CPU). The proposed model combines quantum principle and deep neural networks architecture involving quantum-forward and classical-backward processes; quantum part is in the forward pass, and the traditional neural network handles the backpropagation during model training. This model was tested using a real dataset to assess its practical applicability to machine learning tasks under real-world constraints. Findings The findings reveal the effectiveness of the quantum-classical hybrid approach which achieves an average area under the curve score of 92%, with a precision of 22.6% and a recall of 25.3%. These results suggest that, while quantum noise and Qubit limitations inherent to Noisy Intermediate-Scale Quantum systems impacted prediction accuracy and model generalizability, the quantum-forward process enhanced the model’s ability to identify true positive cases in a complex dataset. Compared to traditional approaches, this model addresses both the stability and predictive demands of highly imbalanced inventory data, although limitations remain in precision and scalability. Originality/value While many open questions remain about the real advantages of quantum computing in applied field of business, this study contributes to the feasibility of leveraging quantum machine learning for complex decision-making problems in supply chain management.
This paper proposes a novel architecture for quantum neural networks (QNNs) inspired by biological neural networks, specifically focusing on adaptive learning capabilities. The core idea is to integrate biological mechanisms such as synaptic plasticity and long-range dependencies into the quantum learning process. The traditional approach to QNN training often relies on gradient-based methods, which can be inefficient and susceptible to local minima. This work introduces a bio-inspired approach that leverages the inherent parallelism and quantum superposition of QNNs to achieve more robust and adaptive learning. We formulate the learning process using a modified Hebbian learning rule combined with a quantum measurement process. The key innovation lies in dynamically adjusting the quantum gates based on the network's internal state, mimicking the neural network's ability to adapt to changing environments. The resulting QNN architecture exhibits enhanced learning speed and improved generalization performance compared to conventional QNNs. The theoretical framework is presented, and the underlying mathematical equations are detailed, providing a robust foundation for further research and development in this field.
Quantum-inspired optimization is a burgeoning field aiming to leverage the principles of quantum mechanics to enhance the efficiency of training neural networks. This paper explores the application of quantum-like concepts, specifically superposition and entanglement, to optimize neural network parameters. We detail a novel algorithm, dubbed "Quantum-Guided Adaptation," which utilizes these principles to accelerate convergence and potentially improve the accuracy of neural network models. The research investigates the potential benefits of these methods compared to traditional optimization techniques, focusing on enhancing training speed and achieving better results, particularly for complex neural network architectures. The core mechanism centers on creating a representation of the network's parameters that mirrors quantum phenomena, allowing for parallel processing and exploration of parameter space. We demonstrate the effectiveness of this approach through simulations and preliminary analysis, suggesting a significant improvement in training time and model accuracy.
This research investigates the performance and efficacy of machine learning models in stock prediction, comparing Artificial Neural Networks (ANNs), Quantum Qubit-based Neural Networks (QQBNs), and Quantum Qutrit-based Neural Networks (QQTNs). By outlining methodologies, architectures, and training procedures, the study highlights significant differences in training times and performance metrics across models. While all models demonstrate robust accuracies above 70%, the Quantum Qutrit-based Neural Network consistently outperforms with advantages in risk-adjusted returns, measured by the Sharpe ratio, greater consistency in prediction quality through the Information Coefficient, and enhanced robustness under varying market conditions. The QQTN not only surpasses its classical and qubit-based counterparts in multiple quantitative and qualitative metrics but also achieves comparable performance with significantly reduced training times. These results showcase the promising prospects of Quantum Qutrit-based Neural Networks in practical financial applications, where real-time processing is critical. By achieving superior accuracy, efficiency, and adaptability, the proposed models underscore the transformative potential of quantum-inspired approaches, paving the way for their integration into computationally intensive fields.
Associative memory, the ability to reconstruct complete information from partial or noisy cues, is a defining feature of human cognition and an enduring objective in artificial intelligence. Classical neural models such as Hopfield networks have long provided insight into distributed storage and retrieval mechanisms, yet they remain constrained by limited storage capacity and susceptibility to noise. Recent developments in quantum computing have motivated investigation of hybrid quantum-classical architectures as alternative approaches to memory representation and retrieval. This study examines how effectively hybrid quantum-classical models can reproduce associative memory functions compared to Hopfield networks, with a particular focus on recall accuracy under varying noise levels, storage capacity, and computational efficiency. Through small-scale experiments using binary patterns and hybrid quantum circuits, we evaluate potential quantum advantages and practical trade-offs. The findings contribute to ongoing discourse in quantum machine learning and cognitive modeling, underscoring both the promise and current limitations of quantum-inspired associative memory systems. Our guiding research question is: To what extent can hybrid quantum–classical models replicate associative memory functions more effectively than classical neural memory models, particularly in terms of recall accuracy under noise and storage capacity?
The field of quantum computing has seen significant progress in recent times, leading to the emergence of innovative methodologies across several areas, particularly in machine learning and neural networks. This research study introduces a quantum-inspired neural network (QINN) that has been particularly developed to improve image recognition capabilities. In contrast to conventional neural networks, the Quantum-inspired Neural Network (QINN) utilizes concepts derived from quantum mechanics, including superposition and entanglement, to process and encode information effectively. The paradigm we propose incorporates quantum bits (qubits) as computing units instead of traditional binary nodes, simultaneously enabling the representation of many states. Moreover, the use of the intrinsic parallelism of quantum mechanics is harnessed to provide expedited and more effective data processing, particularly within the concealed levels of the network. The researchers ran benchmark tests using well-recognized image datasets, including CIFAR-10 and ImageNet. The study's findings indicated that QINN displayed superior accuracy rates compared to traditional methods and revealed faster convergence throughout the training process. Additionally, our quantum-inspired methodology demonstrated significant efficacy in analyzing pictures containing nuanced characteristics, highlighting its potential in practical scenarios where precise identification is of utmost importance. In summary, integrating quantum principles with neural network topologies has the potential for groundbreaking advancement in image recognition skills. QINN is a groundbreaking advancement in this domain, emphasizing the unexplored capacity to use quantum phenomena for sophisticated machine learning objectives. Potential areas for future study are the expansion of network scalability to accommodate bigger datasets, exploration of security measures that are resilient against quantum threats, and investigating hybrid models that integrate both quantum and conventional paradigms to enhance overall performance.