Computer Engineering and Applications Journal

Research on quantum gate circuit neural network and improved learning algorithm

Hou Xua

Published Jan 1, 2014• 1 citation

Abstract

Quantum Gate Circuit Neural Network(QGCNN)is a kind of quantum neural network model, which directly uses quantum theory to design the neural network topology or training algorithms. In the neural network, Momentum update is adding momentum parameter in weight renew and provides a specific inertia while renewing weight vector. It avoids sustained oscillation of weight vector in network training. It introduces the principle of momentum update in the basic learning algorithm of Quantum Gate Circuit Neural Network, proposes Quantum Gate Circuit neural network Momentum update Algorithm(QGCMA). The research shows that QGCMA has 100% convergence rate and enhances convergence speed compared to the basic algorithm with the same learning rate.

Related papers

Quantum Gate Circuit Neural Network Optimization Algorithm Based on Performance Function

Xuan Hou, Shao Song Wan, Rui Zhou Zhenzhen Liu

The current status of Quantum Neural Network (QNN) research is analyzed, it deeply studies the model Quantum Gate Circuit Neural Network (QGCNN) and QGCNN Learning Algorithm (QGCA). Replacing the mean square error function by using the Widrow function and the Rumelhart function, it creates two quantum neural network learning algorithms based on performance function, including Learning Algorithm of QGCNN based on the Widrow functions (WQGCA) and Learning Algorithm of QGCNN based on the Rumelhart functions (RQGCA). New algorithms overcome the inherent defects of the training result is not ideal and unrealistic, which is because the use of mean square error function training network will appear excessive punishment phenomenon. Three algorithms are trained by three data sets. Simulation Experiments on three kinds of algorithms was carried out by using these data sets in the case of the best learning rate. Research prove WQGCA and RQGCA have better pattern classification ability relative to QGCA and RQGCA has a higher classification accuracy than WQGCA.

DEStech Transactions on Computer Science and EngineeringJul 12, 20180 citations

QGA–QGCNN: a model of quantum gate circuit neural network optimized by quantum genetic algorithm

Changqing Gong, Hongsheng Zhu, Abdullah Gani +1 more

Abstract Using global optimization algorithm to optimize the initial weights and thresholds of traditional neural network model can effectively address the problems of premature convergence and lower accuracy. However, the shortcomings such as slower convergence speed and poor local search ability still exist. In order to solve these problems, a neural network model QGA-QGCNN using a Quantum Genetic Algorithm (QGA) to optimize Quantum Gate Circuit Neural Network (QGCNN) is proposed in this paper. In QGA-QGCNN, the initial parameters of QGCNN are optimized for the strong global optimization ability and faster convergence speed by using a QGA. In the proposed model, the normalized results of the predicted sample attributes are transformed into quantum states as the input of the network, and the quantum rotation gate is used to rotate the phase and control the reversal of the target qubits. Finally, the output of the network is obtained by entanglement of multiple qubits in the quantum Controlled-NOT (CNOT) gate. When dealing with more complex problems, the QGCNN model based on quantum computing has specific parallel computing capabilities and can give full play to its ability to blur uncertain problems, thereby improving detection performance. We use the authoritative 10% KDD-CUP99 data set in the field of network intrusion detection to conduct simulation experiments on the proposed QGA-QGCNN model. Experimental results show that the proposed intrusion detection model has lower false alarm rate and significantly accuracy compared to conventional attack detection models. And GQCNN optimized by QGA also improves the convergence performance of the model.

The Journal of SupercomputingMar 24, 20236 citations

A Quantum Neural Network Model and Its Improved Learning Algorithm

Hua Wan

Presents a quantum BP neural network model and its improved learning algorithm.Firstly a quantum neuron is constructed based on the universality of single qubit rotation gate and two-qubit controlled not gate.Secondly,the hide layer is constructed and uses these quantum neurons with the application of the gradient descent algorithm and the output layer is made with traditional neurons,in which weight and bias values are updated according to the improved algorithm of gradient descent momentum and an adaptive learning rate.It is shown that this model and algorithm are superior to the conventional BP networks in two aspects:convergence speed and accuracy by two UCI's data sets examples.

Modern ComputerJan 1, 20100 citations

Learning Algorithm and Application of Quantum Neural Networks with Quantum Weights

Dianbao Mu, Zunyou Guan, Hong Zhang

A novel neural networks model with quantum weights is present.Firstly, based on the information processing modes of biology neuron and quantum computing theory, a quantum neuron model is presented, which is composed of weighting, aggregating, activating, and inspiriting.Secondly the quantum neural networks model based on quantum neuron is constructed in which the input and the output are real vectors; the linked weight and the activation value are qubits.On the basic of the gradient descent algorithm, a learning algorithm of this model is proposed.It is shown that this algorithm is super-linearly convergent under certain conditions and can increase the probability of getting the global optimal solution.Finally, the availability of the model is illustrated in both convergence speed and convergence rate by two application examples of pattern recognition and function approximation.

International Journal of Computer Theory and EngineeringJan 1, 201327 citations

Research on Quantum Adaptive Resonance Theory Neural Network

Xuan Hou

The subject of the paper is Quantum Neural Network. On one hand, introducing quantum theory into the structure or training process of Classical Neural Network with regard to improving structure and capacity of Classical Neural Network, enhancing learning and generalization ability of it. On the other hand, establishing a new topological structure and training algorithm of Quantum Neural Network by the means of quoting the thought, concept and principles of quantum theory directly. In the paper, we summarize the basic model and learning algorithm of quantum neuron, propose the model and learning algorithm of Quantum Adaptive Resonance Theory Neural Network through introducing quantum computing into adaptive resonance theory, apply which in pattern recognition as well. In summary, Quantum Adaptive Resonance Theory Neural Network have an advantage over Classical Adaptive Resonance Theory Neural Network in the positive rate of clustering.

Electronic and Mechanical Engineering and Information TechnologyAug 1, 20118 citations

基于量子态的自适应神经网络

Jincheng Zhang

This paper introduces a novel neural network architecture, termed "Quantum-Aware Adaptive Neural Network" (QANN), which leverages quantum computing principles to dynamically adjust network parameters during training. Traditional neural networks often struggle with optimal parameter settings, leading to suboptimal performance. QANN utilizes quantum circuits to represent and manipulate the input data, enabling a more adaptive and efficient training process. The core mechanism centers around quantum state manipulation to achieve enhanced generalization and predictive accuracy. We explore the potential of QANN to overcome these limitations and provide a promising approach to improve deep learning models. The paper details the design of the QANN architecture, the quantum algorithm employed, and the results obtained through simulations and preliminary experiments. Finally, we discuss the implications of this approach and future research directions.

Sep 3, 20260 citations