Deep learning framework for time series classification based on multiple imaging and hybrid quantum neural networks

Time series classification(TSC)has attracted a lot of attention for time series data mining tasks and has been applied in various fields.With the success of deep learning(DL)in computer vision recognition,people are starting to use deep learning to tackle TSC tasks.Quantum neural networks(QNN)have recently demonstrated their superiority over traditional machine learning in methods such as image processing and natural language processing,but research using quantum neural networks to handle TSC tasks has not received enough attention.Therefore,we proposed a learning framework based on multiple imaging and hybrid QNN(MIHQNN)for TSC tasks.We investigate the possibility of converting 1D time series to 2D images and classifying the converted images using hybrid QNN.We explored the differences between MIHQNN based on single time series imaging and MIHQNN based on the fusion of multiple time series imaging.Four quantum circuits were also selected and designed to study the impact of quantum circuits on TSC tasks.We tested our method on several standard datasets and achieved significant results compared to several current TSC methods,demonstrating the effectiveness of MIHQNN.This research highlights the potential of applying quantum computing to TSC and provides the theoretical and experimental background for future research.

A backdoor attack against quantum neural networks with limited information

Backdoor attacks are emerging security threats to deep neural networks.In these attacks,adversaries manipulate the network by constructing training samples embedded with backdoor triggers.The backdoored model performs as expected on clean test samples but consistently misclassifies samples containing the backdoor trigger as a specific target label.While quantum neural networks(QNNs)have shown promise in surpassing their classical counterparts in certain machine learning tasks,they are also susceptible to backdoor attacks.However,current attacks on QNNs are constrained by the adversary's understanding of the model structure and specific encoding methods.Given the diversity of encoding methods and model structures in QNNs,the effectiveness of such backdoor attacks remains uncertain.In this paper,we propose an algorithm that leverages dataset-based optimization to initiate backdoor attacks.A malicious adversary can embed backdoor triggers into a QNN model by poisoning only a small portion of the data.The victim QNN maintains high accuracy on clean test samples without the trigger but outputs the target label set by the adversary when predicting samples with the trigger.Furthermore,our proposed attack cannot be easily resisted by existing backdoor detection methods.

Approach for Training Quantum Neural Network to Predict Severity of COVID-19 in Patients

Currently,COVID-19 is spreading all over the world and profoundly impacting people’s lives and economic activities.In this paper,a novel approach called the COVID-19 Quantum Neural Network(CQNN)for predicting the severity of COVID-19 in patients is proposed.It consists of two phases:In the first,the most distinct subset of features in a dataset is identified using a Quick Reduct Feature Selection(QRFS)method to improve its classification performance;and,in the second,machine learning is used to train the quantum neural network to classify the risk.It is found that patients’serial blood counts(their numbers of lymphocytes from days 1 to 15 after admission to hospital)are associated with relapse rates and evaluations of COVID-19 infections.Accordingly,the severity of COVID-19 is classified in two categories,serious and non-serious.The experimental results indicate that the proposed CQNN’s prediction approach outperforms those of other classification algorithms and its high accuracy confirms its effectiveness.

Purification in entanglement distribution with deep quantum neural network

Entanglement distribution is important in quantum communication. Since there is no information with value in this process, purification is a good choice to solve channel noise. In this paper, we simulate the purification circuit under true environment on Cirq, which is a noisy intermediate-scale quantum(NISQ) platform. Besides, we apply quantum neural network(QNN) to the state after purification. We find that combining purification and quantum neural network has good robustness towards quantum noise. After general purification, quantum neural network can improve fidelity significantly without consuming extra states. It also helps to obtain the advantage of entangled states with higher dimension under amplitude damping noise. Thus, the combination can bring further benefits to purification in entanglement distribution.

Continuous Variable Quantum MNIST Classifiers—Classical-Quantum Hybrid Quantum Neural Networks

In this paper, classical and continuous variable (CV) quantum neural network hybrid multi-classifiers are presented using the MNIST dataset. Currently available classifiers can classify only up to two classes. The proposed architecture allows networks to classify classes up to nm classes, where n represents cutoff dimension and m the number of qumodes on photonic quantum computers. The combination of cutoff dimension and probability measurement method in the CV model allows a quantum circuit to produce output vectors of size nm. They are then interpreted as one-hot encoded labels, padded with nm - 10 zeros. The total of seven different classifiers is built using 2, 3, …, 6, and 8-qumodes on photonic quantum computing simulators, based on the binary classifier architecture proposed in “Continuous variable quantum neural networks” [1]. They are composed of a classical feed-forward neural network, a quantum data encoding circuit, and a CV quantum neural network circuit. On a truncated MNIST dataset of 600 samples, a 4-qumode hybrid classifier achieves 100% training accuracy.

Application of quantum neural networks in localization of acoustic emission

Due to defects of time-difference of arrival localization,which influences by speed differences of various model waveforms and waveform distortion in transmitting process,a neural network technique is introduced to calculate localization of the acoustic emission source.However,in back propagation（BP） neural network,the BP algorithm is a stochastic gradient algorithm virtually,the network may get into local minimum and the result of network training is dissatisfactory.It is a kind of genetic algorithms with the form of quantum chromosomes,the random observation which simulates the quantum collapse can bring diverse individuals,and the evolutionary operators characterized by a quantum mechanism are introduced to speed up convergence and avoid prematurity.Simulation results show that the modeling of neural network based on quantum genetic algorithm has fast convergent and higher localization accuracy,so it has a good application prospect and is worth researching further more.

Role of Entanglement in Quantum Neural Networks (QNN)

Starting with the theoretical basis of quantum computing, entanglement has been explored as one of the key resources required for quantum computation, the functional dependence of the entanglement measures on spin correlation functions has been established and the role of entanglement in implementation of QNN has been emphasized. Necessary and sufficient conditions for the general two-qubit state to be maximally entangled state (MES) have been obtained and a new set of MES constituting a very powerful and reliable eigen basis (different from magic bases) of two-qubit systems has been constructed. In terms of the MES constituting this basis, Bell’s States have been generated and all the qubits of two-qubit system have been obtained. Carrying out the correct computation of XOR function in neural network, it has been shown that QNN requires the proper correlation between the input and output qubits and the presence of appropriate entanglement in the system guarantees this correlation.

A duplication-free quantum neural network for universal approximation

Different from the concept of universal computation,the universality of a quantum neural network focuses on the ability to approximate arbitrary functions and is an important guarantee for effectiveness.However,conventional approaches of constructing a universal quantum neural network may result in a huge quantum register that is challenging to implement due to noise on a near-term device.To address this,we propose a simple design of a duplication-free quantum neural network whose universality can be rigorously proven.Specifically,instead of using multiple duplicates of the quantum register,our method relies on a single quantum register combined with multiple activation functions to create nonlinearity and achieve universality.Accordingly,our proposal requires significantly fewer qubits with shallower circuits,and hence substantially reduces the resource overhead and the noise effect.In addition,simulations demonstrate that our universality design is able to achieve a better learning accuracy in the presence of noise,illustrating a great potential in solving larger-scale learning problems on near-term devices.

Leveraging Quantum Computing for the Ising Model to Simulate Two Real Systems: Magnetic Materials and Biological Neural Networks (BNNs)

Quantum computing is a field with increasing relevance as quantum hardware improves and more applications of quantum computing are discovered. In this paper, we demonstrate the feasibility of modeling Ising Model Hamiltonians on the IBM quantum computer. We developed quantum circuits to simulate these systems more efficiently for both closed and open boundary Ising models, with and without perturbations. We tested these various geometries of systems in both 1-D and 2-D space to mimic two real systems: magnetic materials and biological neural networks (BNNs). Our quantum model is more efficient than classical computers, which can struggle to simulate large, complex systems of particles.

Learning algorithm and application of quantum BP neural networks based on universal quantum gates

A quantum BP neural networks model with learning algorithm is proposed. First, based on the universality of single qubit rotation gate and two-qubit controlled-NOT gate, a quantum neuron model is constructed, which is composed of input, phase rotation, aggregation, reversal rotation and output. In this model, the input is described by qubits, and the output is given by the probability of the state in which （1） is observed. The phase rotation and the reversal rotation are performed by the universal quantum gates. Secondly, the quantum BP neural networks model is constructed, in which the output layer and the hide layer are quantum neurons. With the application of the gradient descent algorithm, a learning algorithm of the model is proposed, and the continuity of the model is proved. It is shown that this model and algorithm are superior to the conventional BP networks in three aspects： convergence speed, convergence rate and robustness, by two application examples of pattern recognition and function approximation.

Chaotic phenomena in Josephson circuits coupled quantum cellular neural networks

In this paper the nonlinear dynamical behaviour of a quantum cellular neural network （QCNN） by coupling Josephson circuits was investigated and it was shown that the QCNN using only two of them can cause the onset of chaotic oscillation. The theoretical analysis and simulation for the two Josephson-circuits-coupled QCNN have been done by using the amplitude and phase as state variables. The complex chaotic behaviours can be observed and then proved by calculating Lyapunov exponents. The study provides valuable information about QCNNs for future application in high-parallel signal processing and novel chaotic generators.

The characteristics of nonlinear chaotic dynamics in quantum cellular neural networks

With the polarization of quantum-dot cell and quantum phase serving as state variables, this paper does both theoretical analysis and simulation for the complex nonlinear dynamical behaviour of a three-cell-coupled Quantum Cellular Neural Network （QCNN）, including equilibrium points, bifurcation and chaotic behaviour. Different phenomena, such as quasi-periodic, chaotic and hyper-chaotic states as well as bifurcations are revealed. The system＇s bifurcation and chaotic behaviour under the influence of the different coupling parameters are analysed. And it finds that the unbalanced cells coupled QCNN is easy to cause chaotic oscillation and the system response enters into chaotic state from quasi-periodic state by quasi-period bifurcation; however, the balanced cells coupled QCNN also can be chaotic when coupling parameters is in some region. Additionally, both the unbalanced and balanced cells coupled QCNNs can possess hyper-chaotic behaviour. It provides valuable information about QCNNs for future application in high-parallel signal processing and novel ultra-small chaotic generators.

Quantum-Inspired Neural Networks with Application

In this paper, a novel neural network is proposed based on quantum rotation gate and controlled- NOT gate. Both the input layer and the hide layer are quantum-inspired neurons. The input is given by qubits, and the output is the probability of qubit in the state . By employing the gradient descent method, a training algorithm is introduced. The experimental results show that this model is superior to the common BP networks.

Neural Network Based on Quantum Chemistry for Predicting Melting Point of Organic Compounds

有机化合物的融化的点用包括背繁殖的一个联合方法被估计神经网络和量的结构性质关系(QSPR ) 在量化学的参数。反映分子间的力量和分子的对称的十一个描述符被用作输入变量。QSPR 参数用分子的建模和 PM3 被计算半实验的分子的轨道的理论。260 混合物的一个总数被用来训练网络，它用 MatLab 被开发。然后， 73 另外的混合物的融化的点被预言，结果与从文学的试验性的数据相比。学习证明选择人工的神经网络和量的结构性质关系方法为有机化合物的融化的点的评价介绍一种优秀选择，与 5% 的平均绝对偏差。

NEURAL NETWORK FOR THE QUANTUM CORRECTION OF NANOSCALE SOI MOSFETS

The quantum effect of carrier distribution in nanoscale SOI MOSFETs is evident and must be taken into consideration in device modeling and simulation. In this paper, a backpropagation neural network was applied to predict the quantum density of carriers from the classical density, and the influence of the network structure on training speed and accuracy was studied. It was concluded that a carefully trained neural network with two hidden layers using the Levenberg-Marquardt learning algorithm could predict the carrier quantum density of SOI MOSFETs in very good agreement with Schrdinger Poisson equations.

Quantum-Inspired Neural Network with Quantum Weights and Real Weights

To enhance the approximation ability of neural networks, by introducing quantum rotation gates to the traditional BP networks, a novel quantum-inspired neural network model is proposed in this paper. In our model, the hidden layer consists of quantum neurons. Each quantum neuron carries a group of quantum rotation gates which are used to update the quantum weights. Both input and output layer are composed of the traditional neurons. By employing the back propagation algorithm, the training algorithms are designed. Simulation-based experiments using two application examples of pattern recognition and function approximation, respectively, illustrate the availability of the proposed model.

Quantum-Inspired Neural Network with Sequence Input

To enhance the approximation and generalization ability of artificial neural network (ANN) by employing the principles of quantum rotation gate and controlled-not gate, a quantum-inspired neuron with sequence input is proposed. In the proposed model, the discrete sequence input is represented by the qubits, which, as the control qubits of the controlled-not gate after being rotated by the quantum rotation gates, control the target qubit for reverse. The model output is described by the probability amplitude of state in the target qubit. Then a quantum-inspired neural network with sequence input (QNNSI) is designed by employing the sequence input-based quantum-inspired neurons to the hidden layer and the classical neurons to the output layer, and a learning algorithm is derived by employing the Levenberg-Marquardt algorithm. Simulation results of benchmark problem show that, under a certain condition, the QNNSI is obviously superior to the ANN.

Design of a novel hybrid quantum deep neural network in INEQR images classification

We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.

基于集成量子神经网络的大地构造环境判别与分析

量子地球科学是一门崭新的跨学科前缘专业,量子计算和量子机器学习算法为地学大数据的深度挖掘与分析带来了新的契机。其中,量子神经网络是目前最具代表性的研究方向之一,在复杂多源数据处理方面的效率与准确率尤为突出。本文以大地构造环境判别这一关键问题为切入点,利用堆叠集成算法对量子神经网络(Stacking Quantum Neural Network,S-QNN)进行了改进,并分别实现了玄武岩、辉长岩和尖晶石的构造环境智能判别;同时与四种传统算法(SVM、RF、KNN和NB)、经典神经网络(ANN)和传统量子神经网络(QNN)进行对比。结果表明,集成后的S-QNN模型在3类情况下的准确率较最优的传统算法分别提升5.67%、6.19%和13.34%,较普通的QNN模型提升3.11%、4.99%和3.84%,且更具鲁棒性和通用性。该研究反映了所提出的S-QNN在数据处理中的优势,更证实了量子机器学习算法在地球科学研究中的适用性与潜力,为量子科学与地球科学的交叉融合提供了新思路。