© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

Chinese Control Conference (CCC)

Generalized quantum neural predictive networks

Dongxiang Nan, Yunsheng Zhang

Published Jul 1, 2008• 1 citation

Abstract

A nonlinear system such as prediction of coal and methane outbursts, mechanical faults diagnosis and so on, which has the character coupled, randomized and sudden changed to the system variants. It is a difficult problem to predict this kind of nonlinear system with using the accurate and effective approach. We proposed a novel generalized quantum neural predictive networks which can be solved this problem better. To construct the model of a nonlinear system, ANN-PID (artificial neural networks with proportional, integral and derivative) has good nonlinear property, so that it can be constructed the model of the nonlinear system according to the knowledge of history data. And then, according to the projected property, the model can be launched from generalized space to Hilbert space, so that the model with superposition quantum states can be developed. In the quantum mechanicalism, a special state which is so called predictive state can be inverted with more and more hight probability from the superposition stats of sample data, before its predictive results has been produced. We have constructed the model of mapping and a predictive algorithm for the nonlinear system, which can be realized the hidden relations between the system inputs and outputs. The results of calculation shows that generalized quantum neural predictive networks predicts the nonlinear system is effective and accurate.

DOI: 10.1109/chicc.2008.4605237

Related papers

Predictive modeling based on proportional integral derivative neural networks and quantum computation

Dongxiang Nan, Yunsheng Zhang

Quantum Neural Networks (QNN) is a burgeoning new field built upon the combination of classical neural networks and quantum computations, which has many problems needed to solve. The predictive model of QNN is an issue that must be settled to develop QNN based on proportional integral derivative neural networks and quantum computation, which can be so called generalized quantum neural networks (GQNN). Firstly, we describe the theory of quantum computation and neural networks. Secondly, it can realize the algorithm of prediction to construct the modeling of generalized quantum neural networks for those complexity nonlinear systems. Finally, using an example explains the model of generalized quantum neural networks. The computational results shows that GQNN is more effective than conventional neural networks.

World Congress on Intelligent Control and Automation•Jan 1, 2008•3 citations

Generalization Study of Quantum Neural Network

Jinzhe Jiang, Xin Zhang, Li, Chen +2 more

Generalization is an important feature of neural network, and there have been many studies on it. Recently, with the development of quantum compu-ting, it brings new opportunities. In this paper, we studied a class of quantum neural network constructed by quantum gate. In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state. Since all the operations in quan-tum neural networks are unitary, the parameters constitute a hypersphere of Hilbert space. Compared with traditional neural network, the parameter space is flatter. Therefore, it is not easy to fall into local optimum, which means the quantum neural networks have better generalization. In order to validate our proposal, we evaluated our model on three public datasets, the results demonstrated that our model has better generalization than the classical neu-ral network with the same structure.

arXiv:2006.02388•Jun 2, 2020•1 citation

Algorithm and Application of the Quantum-Inspired Neural Network Model

Yang Shu-yu

To enhance the approximation and generalization ability of classical artificial neural networks,a quantum-inspired neural network model,whose input of each dimension is a discrete sequence,is proposed.This model concludes three layers,in which the hidden layer consists of quantum-inspired neurons,and the output layer consists of common neurons.The quantum-inspired neuron consists of the quantum rotation gates and the multi-qubits controlled-rotation gates.By using the information feedback of target qubit from output to input in multi-qubits controlled-rotation gate,the overall memory of input sequences is realized.The output of quantum-inspired neuron is obtained from the entanglements of multi-qubits in controlled-rotation gates.The learning algorithm is designed in detail according to the basic principles of quantum computation.The characteristics of input sequence can be effectively obtained by way ofbreadthanddepth.The simulation results show that,when the input nodes and the length of the sequence satisfy a certain relations,the proposed model is obviously superior to the common artificial neural networks.

Dianzi xuebao•Jan 1, 2014•0 citations

Modeling of Proportional Integral Derivative Neural Networks Based on Quantum Computation

Dongxiang Nan, Yun Sheng Zhang, Xue Qiang Sun

There has been a growing interest in artificial neural networks (ANNs) based on quantum theoretical concepts and techniques due to cognitive science and computer science aspects. The so called Quantum Neural Networks (QNNs) are an exciting area of research in the field of quantum computation and quantum information. We proposed a modeling of Proportional integral derivative neural networks based on quantum computation called QNNs-PID that maps a nonlinear function. We analyze the main algorithms and architecture proposed the modeling of QNNs-PID. The main conclusion is that, up to now, we prove the feed back and back forward algorithm based on quantum computation how to use and give clearly the results for the nonlinear function in the context of QNNs-PID. We simulate an example to show the property of QNNs-PID in nonlinear systems.

Advanced materials research•Jun 1, 2011•0 citations

Artificial neural network based on quantum superposition and its application

Ge Liu, Wenping Ma

Abstract The artificial neural network (ANN), as a powerful data analytical tool, has played a major role in facial recognition, nature language processing (NLP), etc. However, the efficiency of classical networks is seriously challenged by big data, however, the development of quantum theory can be combined with ANN to help overcome this problem. In this paper, we propose a quantum neural network, in which the quantum particle swarm optimization (QPSO) is used to optimize parameters. To analysze the system performance, it has been applied to function fitting and data classification and it is shown by classical simulation and experimentation that the proposed model is more efficient and powerful than ANN for a lot of experimental tasks. We hope that this scheme can be implemented on a quantum computer in the future.

Laser Physics Letters•Jun 25, 2021•1 citation

Sunspot number time series prediction using neural networks with quantum gate nodes

Xuezhong Guan, Ligang Sun, Fangfei Yu +1 more

Sunspot is one of the most basic and obvious activity occurred in the solar photosphere, the number of sunspot have great influence on the production and life as well as climate change. Therefore, studying and predicting of sunspots have important meaning. Aiming at the problem of highly nonlinear in sunspot number and the conventional methods are difficult to convergence, a new prediction method based on neural network with quantum gate is proposed to improve the accuracy of the forecast for Sunspot number time series. The input data is expressed by the qubit, which rotated by the rotation gate, as the control qubits control the hidden layer qubits reverse. In the same way, the hidden layer qubits control the output layer. At last, the probability amplitude of state |1> is regarded as the network output. This proposed method has such advantages as high precision and strong generalization ability, and it is a new promising approach for solving time series prediction problem of sunspot number.

World Congress on Intelligent Control and Automation•Jun 1, 2014•1 citation

A nonlinear system such as prediction of coal and methane outbursts, mechanical faults diagnosis and so on, which has the character coupled, randomized and sudden changed to the system variants. It is a difficult problem to predict this kind of nonlinear system with using the accurate and effective approach. We proposed a novel generalized quantum neural predictive networks which can be solved this problem better. To construct the model of a nonlinear system, ANN-PID (artificial neural networks with proportional, integral and derivative) has good nonlinear property, so that it can be constructed the model of the nonlinear system according to the knowledge of history data. And then, according to the projected property, the model can be launched from generalized space to Hilbert space, so that the model with superposition quantum states can be developed. In the quantum mechanicalism, a special state which is so called predictive state can be inverted with more and more hight probability from the superposition stats of sample data, before its predictive results has been produced. We have constructed the model of mapping and a predictive algorithm for the nonlinear system, which can be realized the hidden relations between the system inputs and outputs. The results of calculation shows that generalized quantum neural predictive networks predicts the nonlinear system is effective and accurate.

Quantum Neural Networks (QNN) is a burgeoning new field built upon the combination of classical neural networks and quantum computations, which has many problems needed to solve. The predictive model of QNN is an issue that must be settled to develop QNN based on proportional integral derivative neural networks and quantum computation, which can be so called generalized quantum neural networks (GQNN). Firstly, we describe the theory of quantum computation and neural networks. Secondly, it can realize the algorithm of prediction to construct the modeling of generalized quantum neural networks for those complexity nonlinear systems. Finally, using an example explains the model of generalized quantum neural networks. The computational results shows that GQNN is more effective than conventional neural networks.

Generalization is an important feature of neural network, and there have been many studies on it. Recently, with the development of quantum compu-ting, it brings new opportunities. In this paper, we studied a class of quantum neural network constructed by quantum gate. In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state. Since all the operations in quan-tum neural networks are unitary, the parameters constitute a hypersphere of Hilbert space. Compared with traditional neural network, the parameter space is flatter. Therefore, it is not easy to fall into local optimum, which means the quantum neural networks have better generalization. In order to validate our proposal, we evaluated our model on three public datasets, the results demonstrated that our model has better generalization than the classical neu-ral network with the same structure.

To enhance the approximation and generalization ability of classical artificial neural networks,a quantum-inspired neural network model,whose input of each dimension is a discrete sequence,is proposed.This model concludes three layers,in which the hidden layer consists of quantum-inspired neurons,and the output layer consists of common neurons.The quantum-inspired neuron consists of the quantum rotation gates and the multi-qubits controlled-rotation gates.By using the information feedback of target qubit from output to input in multi-qubits controlled-rotation gate,the overall memory of input sequences is realized.The output of quantum-inspired neuron is obtained from the entanglements of multi-qubits in controlled-rotation gates.The learning algorithm is designed in detail according to the basic principles of quantum computation.The characteristics of input sequence can be effectively obtained by way ofbreadthanddepth.The simulation results show that,when the input nodes and the length of the sequence satisfy a certain relations,the proposed model is obviously superior to the common artificial neural networks.

There has been a growing interest in artificial neural networks (ANNs) based on quantum theoretical concepts and techniques due to cognitive science and computer science aspects. The so called Quantum Neural Networks (QNNs) are an exciting area of research in the field of quantum computation and quantum information. We proposed a modeling of Proportional integral derivative neural networks based on quantum computation called QNNs-PID that maps a nonlinear function. We analyze the main algorithms and architecture proposed the modeling of QNNs-PID. The main conclusion is that, up to now, we prove the feed back and back forward algorithm based on quantum computation how to use and give clearly the results for the nonlinear function in the context of QNNs-PID. We simulate an example to show the property of QNNs-PID in nonlinear systems.

Abstract The artificial neural network (ANN), as a powerful data analytical tool, has played a major role in facial recognition, nature language processing (NLP), etc. However, the efficiency of classical networks is seriously challenged by big data, however, the development of quantum theory can be combined with ANN to help overcome this problem. In this paper, we propose a quantum neural network, in which the quantum particle swarm optimization (QPSO) is used to optimize parameters. To analysze the system performance, it has been applied to function fitting and data classification and it is shown by classical simulation and experimentation that the proposed model is more efficient and powerful than ANN for a lot of experimental tasks. We hope that this scheme can be implemented on a quantum computer in the future.

Sunspot is one of the most basic and obvious activity occurred in the solar photosphere, the number of sunspot have great influence on the production and life as well as climate change. Therefore, studying and predicting of sunspots have important meaning. Aiming at the problem of highly nonlinear in sunspot number and the conventional methods are difficult to convergence, a new prediction method based on neural network with quantum gate is proposed to improve the accuracy of the forecast for Sunspot number time series. The input data is expressed by the qubit, which rotated by the rotation gate, as the control qubits control the hidden layer qubits reverse. In the same way, the hidden layer qubits control the output layer. At last, the probability amplitude of state |1> is regarded as the network output. This proposed method has such advantages as high precision and strong generalization ability, and it is a new promising approach for solving time series prediction problem of sunspot number.