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

Chinese Journal of Electronics

Quantum Contextuality for Training Neural Networks

Junwei Zhang, Zhao Li

Published Nov 1, 2020• 3 citations
Publisher

Abstract

In the training process of Neural networks (NNs), the selection of hyper-parameters is crucial, which determines the final training effect of the model. Among them, the Learning rate decay (LRD) can improve the learning speed and accuracy; the Weight decay (WD) improves the over-fitting to varying degrees. However, the decay methods still have problems such as hysteresis and stiffness of parameter adjustment, so that the final model will be inferior. Based on the Quantum contextuality (QC) theory, we propose a Quantum contextuality constraint (QCC) to constrain the weights of nodes in NNs to further improve the training effect. In the simplest classification model, we combine this constraint with different methods of LRD and WD to verify that QCC can further improve the training effect on the decay method. The performance of the experiments shows that QCC can significantly improve the convergence and accuracy of the model.

DOI
10.1049/cje.2020.10.003

Related papers

A new training algorithm for Quantum Neural Networks

Jian Sun, Pla Uni

Inspired by the principle of superposing states in quantum mechanics,a new kind of feedforward neural network with single hidden layer was designed and named as Quantum Neural Networks.It has mainly been used for data classification.Multilevel activation functions is adopted in Quantum Neural Networks and a different objective function is used for the learning of quantum intervals of the multilevel hidden units;minimizing the class-conditional variances at the outputs of the hidden units.Quantum Neural Networks is endowed with a special ability of identifying uncertainty in data classification by its unique design.However,as different objective functions are used for the learning of synaptic weights and quantum intervals,conflict is observed in the iterative training process which will cause more iteration times for training and degrades the training results.Using the theory of Constrained Optimization,a new training algorithm is proposed in this paper by introducing penalty function into the steepest descent method.In the new training algorithm, the conflict is removed.Experimental results indicate that the new algorithm can increase the training speed and improve the performance of the trained network remarkably.

Signal Processing•Jan 1, 2011•1 citation

基于量子纠缠的自适应神经网络的训练

Jincheng Zhang

Quantum entanglement, a bizarre phenomenon where two particles become linked and share the same fate regardless of distance, has long been considered a theoretical resource with potential applications in quantum computing and quantum information processing. Recently, the concept of quantum entanglement has begun to be explored in machine learning, particularly in the context of quantum neural networks (QNNs). This paper investigates the feasibility of utilizing quantum entanglement to accelerate the training process of neural networks. We propose a novel training strategy that leverages entangled quantum states to enhance the learning dynamics, aiming to overcome limitations inherent in classical neural network training. This work presents a framework for utilizing entangled quantum states to dynamically adjust the weights and biases of a neural network, potentially leading to faster convergence and improved model performance. The core mechanism of this approach involves establishing entangled correlations between nodes and connections within the network, which allows for more efficient exploration of the solution space. We demonstrate the effectiveness of this method through simulations and preliminary experiments, suggesting a promising avenue for advancing the field of quantum machine learning.

•Sep 4, 2026•0 citations

Quantum-Inspired Optimization of Neural Network Training Dynamics

Jincheng Zhang

Training deep neural networks remains a computationally intensive and often challenging process. Traditional optimization methods, such as stochastic gradient descent (SGD) and its variants, frequently struggle to escape local minima and converge to optimal solutions, leading to suboptimal network performance. This paper proposes a novel approach to neural network training that leverages principles inspired by quantum mechanics. Specifically, we investigate the application of quantum-inspired optimization techniques, including simulated annealing and quantum walks, to dynamically adjust the training process. The core idea is to mimic the probabilistic exploration inherent in quantum systems to effectively navigate the complex loss landscape of neural networks. We formulate the training process as a quantum-inspired optimization problem, where the network's weights are treated as quantum bits (Qubits) and the optimization algorithm seeks to find the lowest energy state, analogous to finding the minimum loss. The proposed method demonstrates the potential for accelerating convergence and improving the overall accuracy of neural networks compared to conventional optimization strategies. Our analysis focuses on the key aspects of the approach, including the mathematical formulation of the quantum-inspired optimization problem and the selection of appropriate parameters to govern the exploration and exploitation phases. We present a theoretical framework for understanding the dynamics of this approach and discuss potential avenues for further research, including hybrid quantum-classical algorithms and the integration of quantum computing hardware.

•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

基于量子自适应的神经网络架构优化

Jincheng Zhang

This paper presents a novel neural network architecture optimization framework based on quantum self-adaptation. Traditional neural network training often relies on manually tuning hyperparameters, which can be time-consuming and suboptimal. We introduce a quantum self-adaptation mechanism that dynamically adjusts network parameters during training, optimizing the model's performance and efficiency. This framework leverages the inherent advantages of quantum computation to explore a larger parameter space and identify optimal configurations more efficiently than classical methods. We demonstrate the effectiveness of this approach through extensive experiments on several benchmark datasets. The results indicate a significant improvement in model accuracy and training speed compared to state-of-the-art methods. We also explore the potential of this quantum-inspired optimization technique for a broader range of neural network architectures.

•Sep 6, 2026•0 citations

Hybrid quantum neural network based on weight remapping and its applications

Yumin Dong, Shuang Wu

Abstract In order to explore the possibility of cross-fertilization between quantum computing and neural networks, and to analyse the effects of multiple weight remapping functions on the model performance, this article proposes two hybrid models based on weight remapping: the hybrid quantum neural network (HQNN-WR) and the hybrid quantum convolutional neural network (HQCNN-WR). The HQNN-WR model uses a two-layer fully connected network to process the input features, performs feature transformation by applying multiple weight remapping functions, and subsequently passes the processed features to the quantum neural network for computation, and finally outputs the classification results. The experimental results show that the model significantly improves the classification accuracy on Iris, Wine and Breast datasets and the convergence speed is faster. The HQCNN-WR model integrates convolutional layers, pooling layers, and fully connected layers, and prevents over-fitting through a dropout layer, and exhibits excellent performance in binary classification tasks on MNIST and KMNIST datasets. The model effectively mitigates the over-fitting problem on small sample datasets and enhances the robustness and generalization ability of the model while improving the digit recognition accuracy. By comparing different models, this article also demonstrates their significant effects on the performance of hybrid quantum neural networks, providing a new theoretical basis and experimental support for the optimization and application of quantum machine learning methods.

Physica Scripta•Dec 5, 2024•2 citations
In the training process of Neural networks (NNs), the selection of hyper-parameters is crucial, which determines the final training effect of the model. Among them, the Learning rate decay (LRD) can improve the learning speed and accuracy; the Weight decay (WD) improves the over-fitting to varying degrees. However, the decay methods still have problems such as hysteresis and stiffness of parameter adjustment, so that the final model will be inferior. Based on the Quantum contextuality (QC) theory, we propose a Quantum contextuality constraint (QCC) to constrain the weights of nodes in NNs to further improve the training effect. In the simplest classification model, we combine this constraint with different methods of LRD and WD to verify that QCC can further improve the training effect on the decay method. The performance of the experiments shows that QCC can significantly improve the convergence and accuracy of the model.
Inspired by the principle of superposing states in quantum mechanics,a new kind of feedforward neural network with single hidden layer was designed and named as Quantum Neural Networks.It has mainly been used for data classification.Multilevel activation functions is adopted in Quantum Neural Networks and a different objective function is used for the learning of quantum intervals of the multilevel hidden units;minimizing the class-conditional variances at the outputs of the hidden units.Quantum Neural Networks is endowed with a special ability of identifying uncertainty in data classification by its unique design.However,as different objective functions are used for the learning of synaptic weights and quantum intervals,conflict is observed in the iterative training process which will cause more iteration times for training and degrades the training results.Using the theory of Constrained Optimization,a new training algorithm is proposed in this paper by introducing penalty function into the steepest descent method.In the new training algorithm, the conflict is removed.Experimental results indicate that the new algorithm can increase the training speed and improve the performance of the trained network remarkably.
Quantum entanglement, a bizarre phenomenon where two particles become linked and share the same fate regardless of distance, has long been considered a theoretical resource with potential applications in quantum computing and quantum information processing. Recently, the concept of quantum entanglement has begun to be explored in machine learning, particularly in the context of quantum neural networks (QNNs). This paper investigates the feasibility of utilizing quantum entanglement to accelerate the training process of neural networks. We propose a novel training strategy that leverages entangled quantum states to enhance the learning dynamics, aiming to overcome limitations inherent in classical neural network training. This work presents a framework for utilizing entangled quantum states to dynamically adjust the weights and biases of a neural network, potentially leading to faster convergence and improved model performance. The core mechanism of this approach involves establishing entangled correlations between nodes and connections within the network, which allows for more efficient exploration of the solution space. We demonstrate the effectiveness of this method through simulations and preliminary experiments, suggesting a promising avenue for advancing the field of quantum machine learning.
Training deep neural networks remains a computationally intensive and often challenging process. Traditional optimization methods, such as stochastic gradient descent (SGD) and its variants, frequently struggle to escape local minima and converge to optimal solutions, leading to suboptimal network performance. This paper proposes a novel approach to neural network training that leverages principles inspired by quantum mechanics. Specifically, we investigate the application of quantum-inspired optimization techniques, including simulated annealing and quantum walks, to dynamically adjust the training process. The core idea is to mimic the probabilistic exploration inherent in quantum systems to effectively navigate the complex loss landscape of neural networks. We formulate the training process as a quantum-inspired optimization problem, where the network's weights are treated as quantum bits (Qubits) and the optimization algorithm seeks to find the lowest energy state, analogous to finding the minimum loss. The proposed method demonstrates the potential for accelerating convergence and improving the overall accuracy of neural networks compared to conventional optimization strategies. Our analysis focuses on the key aspects of the approach, including the mathematical formulation of the quantum-inspired optimization problem and the selection of appropriate parameters to govern the exploration and exploitation phases. We present a theoretical framework for understanding the dynamics of this approach and discuss potential avenues for further research, including hybrid quantum-classical algorithms and the integration of quantum computing hardware.
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 paper presents a novel neural network architecture optimization framework based on quantum self-adaptation. Traditional neural network training often relies on manually tuning hyperparameters, which can be time-consuming and suboptimal. We introduce a quantum self-adaptation mechanism that dynamically adjusts network parameters during training, optimizing the model's performance and efficiency. This framework leverages the inherent advantages of quantum computation to explore a larger parameter space and identify optimal configurations more efficiently than classical methods. We demonstrate the effectiveness of this approach through extensive experiments on several benchmark datasets. The results indicate a significant improvement in model accuracy and training speed compared to state-of-the-art methods. We also explore the potential of this quantum-inspired optimization technique for a broader range of neural network architectures.
Abstract In order to explore the possibility of cross-fertilization between quantum computing and neural networks, and to analyse the effects of multiple weight remapping functions on the model performance, this article proposes two hybrid models based on weight remapping: the hybrid quantum neural network (HQNN-WR) and the hybrid quantum convolutional neural network (HQCNN-WR). The HQNN-WR model uses a two-layer fully connected network to process the input features, performs feature transformation by applying multiple weight remapping functions, and subsequently passes the processed features to the quantum neural network for computation, and finally outputs the classification results. The experimental results show that the model significantly improves the classification accuracy on Iris, Wine and Breast datasets and the convergence speed is faster. The HQCNN-WR model integrates convolutional layers, pooling layers, and fully connected layers, and prevents over-fitting through a dropout layer, and exhibits excellent performance in binary classification tasks on MNIST and KMNIST datasets. The model effectively mitigates the over-fitting problem on small sample datasets and enhances the robustness and generalization ability of the model while improving the digit recognition accuracy. By comparing different models, this article also demonstrates their significant effects on the performance of hybrid quantum neural networks, providing a new theoretical basis and experimental support for the optimization and application of quantum machine learning methods.