神经计算与量子神经计算的研究综述

神经计算科学是从信息科学的角度,用计算的方法研究神经网络如何模仿和延伸人脑活动的机理及实现类脑智能信息系统的问题。量子神经计算是量子计算与神经计算相结合的产物。文中主要阐述了神经计算的研究现状,在其基础上对量子神经计算的概念及模型进行了介绍,综述了国内外的研究动态与发展趋势。     

量子计算在神经网络中的应用研究

本文首先在介绍量子计算基本理论的基础上,探讨其在神经网络中的融合与应用;同时针对典型网络模型进行了具体的可行性研究与总结。最后就其两者的融合后的实际应用进行了深入研究。     

乳腺癌的量子神经元诊断

量子神经计算结合了传统神经计算与量子计算的优点,是新的信息处理技术之一。本文构造出一个三层量子神经网络,并将它应用于乳腺癌的诊断。实验结果表明,量子神经网络明显优于传统神经网络,如自组织神经网络、概率神经网络以及支持向量机等,不仅对正样本的识别率达到最高,可以较好的识别出乳腺癌患者,同时还可以很好的识别出非乳腺癌病例,其诊断正确率是最高的。     

量子神经网络在电力谐波检测中的应用

该文利用复数BP学习算法,构造出量子神经元模型[1],并结合神经网络技术与量子理论,生成更有效的泛化和学习能力的量子神经网络。基于三层量子神经网络实现对谐波参数的检测,并以3次谐波和5次谐波为例,描述了该网络的训练流程和训练样本的构成。量子神经网络的实现采用Matlab进行编程,首先利用训练样本训练量子网络,之后检测构造的未训练样本数据集,通过仿真结果验证了该方法的可行性。该方法在谐波检测中具有较高的灵活性和精度,且对采样数目没有严格的限制,训练好的量子神经网络模型可用于谐波源固定的场合。     

基于受控旋转门的量子神经网络模型算法及应用

提出一种量子神经网络模型及算法．首先借鉴受控非门的含义提出一种受控量子旋转门,基于该门的物理意义,提出一种量子神经元模型,该模型包含对输入量子比特相位的旋转角度和对旋转角度的控制量两种设计参数;然后基于上述量子神经元提出一种量子神经网络模型,基于梯度下降法详细设计了该模型的学习算法：最后通过模式识别和时间序列预测两个仿...     

一种量子神经网络模型学习算法及应用

提出一种量子神经网络模型及学习算法. 首先基于生物神经元信息处理机制和量子计算原理构造出一种量子神经元, 该神经元由加权、聚合、活化、激励四部分组成. 然后由量子神经元构造出三层量子神经网络模型, 其输入和输出为实值向量, 权值和活性值为量子比特. 基于梯度下降法构造了该模型的超线性收敛学习算法. 通过模式识别和函数逼近两种仿真结果表明该模型及算法是有效的.     

基于量子门组的量子神经网络模型及其应用

为进一步提高量子神经网络的性能,结合目前神经网络机理的研究进展,提出了一种基于量子门组的量子神经元模型,建立了量子门组量子神经网络（Quantum Gate Set Neural Network,QGSNN）。该算法由输入层、隐含层和输出层组成,该算法将转换后的量子态训练样本作为输入。利用量子旋转门和通用量子门完成旋转、选择、翻转和聚合等一系列操作,并完成了网络参数的更新。将训练后的结果输出。QGSNN算法的泛化能力在数学上得到了证明,并利用两个仿真实验对该方法进行验证。实验结果表明,与普通神经网络和普通量子神经网络相比,QG-SNN算法在泛化性能、鲁棒性、准确率和执行时间等方面具有较好的效果。     

一种量子衍生神经网络模型

为提高神经网络的逼近能力,通过在普通BP网络中引入量子旋转门,提出了一种新颖的量子衍生神经网络模型. 该模型隐层由量子神经元组成,每个量子神经元携带一组量子旋转门,用于更新隐层的量子权值,输入层和输出层均为普通神经元. 基于误差反传播算法设计了该模型的学习算法. 模式识别和函数逼近的实验结果验证了提出模型及算法的有效性.     

基于多级神经元的神经网络及其在分类中的应用

为了提高前向神经网络的分类能力,该文将多级神经元扩展使用到多层感知器的输出层和隐含层中,并提出了量子神经网络的学习算法。通过一个实际的分类问题实验验证了该方法的有效性。实验表明,无论输出层或隐含采用多级神经元,都可以带来分类能力的提高。而当输出层采用多级神经元时,还可以导致连接的减少和训练速度的加快。     

Qubit neural network and its learning efficiency

Neural networks have attracted much interest in the last two decades for their potential to realistically describe brain functions, but so far they have failed to provide models that can be simulated in a reasonable time on computers; rather they have been limited to toy models. Quantum computing is a possible candidate for improving the computational efficiency of neural networks. In this framework of quantum computing, the Qubit neuron model, proposed by Matsui and Nishimura, has shown a high efficiency in solving problems such as data compression. Simulations have shown that the Qubit model solves learning problems with significantly improved efficiency as compared to the classical model. In this paper, we confirm our previous results in further detail and investigate what contributes to the efficiency of our model through 4-bit and 6-bit parity check problems, which are known as basic benchmark tests. Our simulations suggest that the improved performance is due to the use of superposition of neural states and the use of probability interpretation in the observation of the output states of the model.     

Binary image denoising using a quantum multilayer self organizing neural network

Several classical techniques have evolved over the years for the purpose of denoising binary images. But the main disadvantages of these classical techniques lie in that an a priori information regarding the noise characteristics is required during the extraction process. Among the intelligent techniques in vogue, the multilayer self organizing neural network (MLSONN) architecture is suitable for binary image preprocessing tasks.In this article, we propose a quantum version of the MLSONN architecture. Similar to the MLSONN architecture, the proposed quantum multilayer self organizing neural network (QMLSONN) architecture comprises three processing layers viz., input, hidden and output layers. The different layers contains qubit based neurons. Single qubit rotation gates are designated as the network layer interconnection weights. A quantum measurement at the output layer destroys the quantum states of the processed information thereby inducing incorporation of linear indices of fuzziness as the network system errors used to adjust network interconnection weights through a quantum backpropagation algorithm.Results of application of the proposed QMLSONN are demonstrated on a synthetic and a real life binary image with varying degrees of Gaussian and uniform noise. A comparative study with the results obtained with the MLSONN architecture and the supervised Hopfield network reveals that the QMLSONN outperforms the MLSONN and the Hopfield network in terms of the computation time.     

代价敏感概率神经网络及其在故障诊断中的应用

针对传统的分类算法人多以误分率最小化为目标,忽略了误分类型之间的差别和数据集的非平衡性的问题,提出代价敏感概率神经网络算法.该算法将代价敏感机制引入概率神经网络,用期望代价取代误分率,以期望代价最小化为目标,基于期望代价最小的贝叶斯决策规则预测新样本类别.采用工业现场数据和数据集German Credit验证了该算法的有效性.实验结果表明,该算法具有故障识别率高、泛化能力强、建模时间短等特点.     

Double chains quantum genetic algorithm with application to neuro-fuzzy controller design

This paper proposes a double chains quantum genetic algorithm (DCQGA), and shows its application in designing neuro-fuzzy controller. In this algorithm, the chromosomes are composed of qubits whose probability amplitudes comprise gene chains. The quantum chromosomes are evolved by quantum rotation gates, and mutated by quantum non-gates. For the direction of rotation angle of quantum rotation gates, a simple determining method is proposed. The magnitude of rotation angle is computed by integrating the gradient of the fitness function. Furthermore, a normalized neuro-fuzzy controller (NNFC) is constructed and designed automatically by the proposed algorithm. Application of the DCQGA-designed NNFC to real-time control of an inverted pendulum system is discussed. Experimental results demonstrate that the designed NNFC has very satisfactory performance.     

Hopfield神经网络在机组组合问题中的应用

提出利用多层Hopfield神经网络求解机组组合优化问题。通过构造合适的能量函数使得单层Hopfield神经网络可以解决某一时刻的机组出力问题,与之相对应的多层神经网络可以解决任意时间段的机组出力问题。多层Hopfield神经网络的层数由所需求解问题的时间段确定。给出单层及多层神经网络的能量函数及求解算法,能量函数考虑到机组升降功率和出力上下限的约束。通过对已有文献的算例进行计算比对,所得结果和遗传算法基本一致,但Hopfield神经网络通过解微分方程组来确定最优解,计算时间相对较少。     

灰色神经网络模型及其应用

灰色建模要求的样本点少,不必有较好的分布规律,而且计算量少,操作简便。而BP网络学习样本时,会反馈校正输出的误差,具有并行计算、分布式信息存储、强容错力、自适应学习功能等优点。本文将灰色预测建模和神经网络技术融合起来,建立灰色神经网络模型(GNNM)。提出计算残差序列和新的预测值的公式。用于发酵动力学预测,结果表明,灰色神经网络模型在预测精度方面优于常规灰色模型。该模型的算法概念明确,计算简便,有较高的拟合和预测精度,拓宽了灰色模型的应用范围。     

粗集神经网络及其在智能信息处理领域的应用

通过对近10年发展起来的粗集神经网络集成技术的总结和归纳,可将粗集神经网络集成技术分为3种:粗集神经网络混合系统、粗边界神经网络和粗-颗粒神经网络.介绍了每种集成技术的研究现状,分析和阐述了其原理及特点.最后,总结了当前粗集神经网络集成技术中需关注的一些问题,并指出了进一步研究的方向.     

An evaluation of quantum neural networks in the detection of epileptic seizures in the neonatal electroencephalogram

This paper presents the results of an experimental study that evaluated the ability of quantum neural networks (QNNs) to capture and quantify uncertainty in data and compared their performance with that of conventional feedforward neural networks (FFNNs). In this work, QNNs and FFNNs were trained to classify short segments of epileptic seizures in neonatal EEG. The experiments revealed significant differences between the internal representations created by trained QNNs and FFNNs from sample information provided by the training data. The results of this experimental study also confirmed that the responses of trained QNNs are more reliable indicators of uncertainty in the input data compared with the responses of trained FFNNs.