The training of neural networks to model manufacturing processes

Neural networks have been increasingly used in various areas of manufacturing. Modelling of manufacturing processes, to allow experimentation on the model, is one of the areas in which successful applications have been reported. Most literature in this area is focused on network results. This paper concentrates on methods for training neural networks to model complex manufacturing processes. It summarises the use of neural network for process modelling in the past decade and provides some detailed guidelines for network training. A case study of a complex forming process is used to demonstrate a real implementation case in industry, and the issues arising from this case are discussed.     

Perceptrons with polynomial post-processing

We introduce tensor product neural networks, composed of a layer of univariate neurons followed by a net of polynomial post-processing. We look at the general approximation properties of these networks observing in particular their relationship to the Stone-Weierstrass theorem for uniform function algebras. The implementation of the post-processing as a two-layer network, with logarithmic and exponential neurons leads to potentially important ‘generalized’ product networks, which however require a complex approximation theory of Müntz-Szasz-Ehrenpreis type. A back-propagation algorithm for product networks is presented and used in three computational experiments. In particular, approximation by a sigmoid product network is compared to that of a single layer radial basis network, and a multiple layer sigmoid network. An additional experiment is conducted, based on an operational system, to further demonstrate the versatility of the architecture.     

专家神经网络的构造研究

专家神经网络是由专家系统产生出的事件驱动无环路神经对象网络。这些神经对象处理信息的非线性复合函数比正常的神经网络结点处理器更复杂。本文研究了无环路网络的ＢＰ学习算法,这一算法将传统ＢＰ算法与专家神经网络特征结合起来,提供了一种获取知识的方法。     

基于神经网络的异构网络向量化表示方法

当网络中存在不同类型的对象时,对象与对象之间的关系会变得多种多样,网络的结构也会变得更为复杂。针对网络的异构化问题,提出了一种基于神经网络的异构网络向量化表示方法。针对具有图片和文本两种类型对象的异构网络,采用多层次的卷积网络将图片映射到一个潜在的特征空间,采用全连接的神经网络将文本对象也映射到相同的特征空间。在该特征空间内,图片与图片、文本与文本以及图片和文本之间的相似性采用相同的距离计算方法。在实验中,应用提出的方法进行异构网络的多种应用测试,结果表明提出的方法是有效的。     

神经网络在数据挖掘中的应用研究

针对神经网络在社保数据挖掘项目中对数据预处理的具体应用,讨论了神经网络在数据挖掘中的作用。尽管神经网络具有结构复杂、网络训练时间长、结果表示不容易理解等不利之处,但其错误率低的优点是其它方法所不及的,并在数据挖掘采用的方法中具有其优势。     

Acquisition of state transitions and concept formation in neural networks

Searching of state transitions is an important subject of problem solving in artificial intelligence, computer science, engineering and operations research. In artificial intelligence, a breadth-first search is optimal, with uniform cost, but it takes considerable time to obtain a solution. Neural networks process state transitions in parallel with learning ability. The authors have developed a search procedure for state transitions, that resembles a breadth-first search, using neural networks. First, the input pattern states are self-organized in the neural network, which consists of a Kohonen layer followed by a state-planning layer. The state-planning layer makes lateral connections between the cells of transitions. Then, the initial and the target states are given as a problem. The network shows an optimal transition pathway of states in the neuron firings. Next, the state-transition procedure is developed for the formation of a concept for action planning. Here, as the action planning, an integration between the symbols and the action pattern is carried out in the extended neural network.     

Reconstruction of chaotic dynamics via a network of stochastic resonance neurons and its application to speech

Recently, a great deal of attention has been paid tostochastic resonance as a new framework to understand sensory mechanisms of biological systems. Stochastic resonance explains important properties of sensory neurons that accurately detect weak input stimuli by using a small amount of internal noise. In particular, Collins et al. reported that a network of stochastic resonance neurons gives rise to a robust sensory function for detecting a variety of complex input signals. In this study, we investigate effectiveness of such stochastic resonance neural networks to chaotic input signals. Using the Rössler equations, we analyze the network's capability to detect chaotic dynamics. We also apply the stochastic resonance network systems to speech signals, and examine a plausibility of the stochastic resonance neural network as a possible model for the human auditory system.     

神经计算在故障诊断中的应用

故障诊断的基本问题是故障的分类问题。神经网络有很强的分类能力，并且有着特有的联想记忆、并行推理和抗干扰的能力，这些使得它成为研究故障诊断的一个新的课题。本文介绍了神经网络几种典型的模型：ＢＰ网、Ｈｏｐｆｉｅｄ、网、ＢＡＭ网和ＡＲＴ网在故障诊断中的应用。     

A neural network trained to identify the presence of myocardial infarction bases diagnostic decision on nonlinear relationships between input variables

To determine whether an artificial neural network trained to recognize the presence of acute myocardial infarction makes clinical decisions based on nonlinear relationships it establishes between inputted information, a linear and nonlinear network with identical number of input nodes were trained and then tested on identical pattern sets. The ratio of residual variances between the two networks was 0.726. The linear and nonlinear networks made 21 and 9 errors, respectively, on 350 test patterns. The use of nonlinear relationships was further studied by trending the quantitative effect on network output resulting from the modification of single clinical input variables in 706 specific patterns derived from patients presenting with anterior chest pain. This revealed that the distribution of the effect on network output was bimodally distributed in 8 of the 20 clinical input variables utilized by the network. The basis for this distribution was due to the network placing markedly different diagnostic importance on the same variable in different patterns. This appears to be the first instance in which nonlinear logic has been shown to improve upon clinical decision-making.     

神经网络模式识别用于金属间化合物三元填隙d88结构形成条件的判别

本文将神经网络模式识别用于金属间化合物3元填隙d88结构形成条件的判别;神经网络由3层组成,训练用后向传播算法。为了评价所得模型的行为,使用了交叉验证法。计算结果表明,当适当的键参数作为输入时,71种化合物能被正确地分类,且隐层节点数经优选后可以提高分类的准确率,减少计算时间。     

A taxonomy for wavelet neural networks applied to nonlinear modelling

This article presents a novel classification of wavelet neural networks based on the orthogonality/non-orthogonality of neurons and the type of nonlinearity employed. On the basis of this classification different network types are studied and their characteristics illustrated by means of simple one-dimensional nonlinear examples. For multidimensional problems, which are affected by the curse of dimensionality, the idea of spherical wavelet functions is considered. The behaviour of these networks is also studied for modelling of a low-dimension map.     

基于郭涛算法的演化神经网络

提出了一种新的演化神经网络算法GTEANN,该算法基于高效的郭涛算法,同时完成在网络结构空间和权值空间的搜索,以实现前馈神经网络的自动化设计。本方法采用的编码方案直观有效,基于该编码表示,神经网络的学习过程是一个复杂的混合整实数非线性规划问题,例如杂交操作包括网络的同构和规整处理。初步实验结果表明该方法收敛,能够达到根据训练样本自动优化设计多层前馈神经网络的目的。     

一种基于数据并行的过程神经网络训练算法

针对过程神经网络时空聚合运算机制复杂、学习周期长的问题,提出了一种基于数据并行的过程神经网络训练算法。该方法基于梯度下降的批处理训练方式,应用MPI并行模式进行算法设计,在局域网内实现多台计算机的机群并行计算。文中给出了基于数据并行的过程神经网络训练算法和实现机制,对不同规模的训练函数样本集和进程数进行了对比实验,并对加速比、并行效率等算法性质进行了分析。实验结果表明,根据网络和样本规模适当选取并行粒度,算法可较大提高过程神经网络的训练效率。     

带偏置的选择性神经网络集成构造方法

训练多个神经网络并将其结果进行合成,能显著地提高神经网络系统的泛化能力。本文提出了一种带偏置的选择性神经网络集成构造方法。对个体网络引入偏置项,增加可选网络的数量。选择部分网络集成,改善网络集成的性能。把个体网络的偏置项统一为集成偏置项,在训练出个体神经网络后,使用遗传算法选择部分网络集成,同时确定集成偏置项。理论分析和实验结果表明,该方法能够取得很好的网络集成效果。     

基于复杂网络描述的图像深度卷积分类方法

为了在不增加较多计算量的前提下,提高卷积网络模型用于图像分类的正确率,提出了一种基于复杂网络模型描述的图像深度卷积分类方法。首先,对图像进行复杂网络描述,得到不同阈值下的复杂网络模型度矩阵;然后,在图像度矩阵描述的基础上,通过深度卷积网络得到特征向量;最后,根据得到的特征向量进行K近邻（KNN）分类。在ILSVRC2014数据库上进行了验证实验,实验结果表明,所提出的模型具有较高的正确率和较少的迭代次数。     

网络应用程序由IPv4向IPv6迁移策略的研究

本文从应用程序的角度来探讨IPv4网络向IPv6网络过渡的问题,着重论述Pv4网络应用程序向IPv6网络应用程序迁移的三种策略。在研究它们各自优缺点的基础上,得出在过渡时期如何正确使用它们的一些结论。同时,本文还探讨了设计协议无关的网络应用程序的关键的、具有共性的一些原则,对设计与开发协议无关的网络应用程序的具有指导意义。     

一种基于数据并行的过程神经网络训练算法

针对过程神经网络时空聚合运算机制复杂、学习周期长的问题,提出了一种基于数据并行的过程神经网络训练算法。该方法基于梯度下降的批处理训练方式,应用MPI并行模式进行算法设计,在局域网内实现多台计算机的机群并行计算。文中给出了基于数据并行的过程神经网络训练算法和实现机制,对不同规模的训练函数样本集和进程数进行了对比实验,并对加速比、并行效率等算法性质进行了分析。实验结果表明,根据网络和样本规模适当选取并行粒度,算法可较大提高过程神经网络的训练效率。     

基于广义回归网络的动态权重回归型神经网络集成方法研究*

神经网络集成技术能有效地提高神经网络的预测精度和泛化能力,已成为机器学习和神经计算领域的一个研究热点。针对回归分析问题提出了一种动态确定结果合成权重的神经网络集成构造方法,在训练出个体神经网络之后,根据各个体网络在输入空间上对训练样本的预测误差,应用广义回归网络来动态地确定各个体网络在特定输入空间上的权重。实验结果表明,与传统的简单平均和加权平均方法相比,本集成方法能取得更好的预测精度。     

基于AHP和ANN的网络安全综合评价方法研究

网络安全评价是一项复杂的系统工程。论文采用层次分析法(AHP),对影响网络安全的各种因素进行了深入研究,确立了网络安全综合评价指标体系,提出了人工神经网络(ANN)安全评价模型,为全面评价计算机网络安全状况提供了新的思路和方法。     

A constructive algorithm to synthesize arbitrarily connected feedforward neural networks

In this work we present a constructive algorithm capable of producing arbitrarily connected feedforward neural network architectures for classification problems. Architecture and synaptic weights of the neural network should be defined by the learning procedure. The main purpose is to obtain a parsimonious neural network, in the form of a hybrid and dedicate linear/nonlinear classification model, which can guide to high levels of performance in terms of generalization. Though not being a global optimization algorithm, nor a population-based metaheuristics, the constructive approach has mechanisms to avoid premature convergence, by mixing growing and pruning processes, and also by implementing a relaxation strategy for the learning error. The synaptic weights of the neural networks produced by the constructive mechanism are adjusted by a quasi-Newton method, and the decision to grow or prune the current network is based on a mutual information criterion. A set of benchmark experiments, including artificial and real datasets, indicates that the new proposal presents a favorable performance when compared with alternative approaches in the literature, such as traditional MLP, mixture of heterogeneous experts, cascade correlation networks and an evolutionary programming system, in terms of both classification accuracy and parsimony of the obtained classifier.