Neural networks and graph theory

The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.     

Using an artificial neural network to detect activations during ventricular fibrillation.

Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92% of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may beuseful for identifying activation during ventricular fibrillation.     

基于模糊进化规划和分层方法的神经网络设计方法

本文提出一种模糊进化规划，用于前向神经网络的设计．该方法通过对神经元的部分解群体的进化，缩短了个体的编码长度，显著地减轻了计算量，同时这种方法不但能够在很大程度上简化适应值的计算，更重要的是能够降低适应值空间的复杂性，从而能够加速进化算法收敛到全局最优点．仿真结果显示，本文提出的算法能够有效抑制进化规划算法初期收敛的发生，有效地提高多层前向神经网络收敛精度，并可获得更为简洁的网络结构．     

Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations

The prediction of tropospheric ozone concentrations is very important due to the negative impacts of ozone on human health, climate and vegetation. The development of models to predict ozone concentrations is thus very useful because it can provide early warnings to the population and also reduce the number of measuring sites. The aim of this study was to predict next day hourly ozone concentrations through a new methodology based on feedforward artificial neural networks using principal components as inputs. The developed model was compared with multiple linear regression, feedforward artificial neural networks based on the original data and also with principal component regression. Results showed that the use of principal components as inputs improved both models prediction by reducing their complexity and eliminating data collinearity.     

Sigmoidal Function Classes for Feedforward Artificial Neural Networks

The role of activation functions in feedforward artificial neural networks has not been investigated to the desired extent. The commonly used sigmoidal functions appear as discrete points in the sigmoidal functional space. This makes comparison difficult. Moreover, these functions can be interpreted as the (suitably scaled) integral of some probability density function (generally taken to be symmetric/bell shaped). Two parameterization methods are proposed that allow us to construct classes of sigmoidal functions based on any given sigmoidal function. The suitability of the members of the proposed class is investigated. It is demonstrated that all members of the proposed class(es) satisfy the requirements to act as an activation function in feedforward artificial neural networks.     

DESIGN OF SUPERVISORY CONTROL FUNCTIONS BASED ON FEEDFORWARD NEURAL NETWORKS

This paper presents the results of the research concerning possibilities of applying artificial neural networks for fault diagnosis, state estimation, and prediction in the gas pipeline transmission network. The influence of several factors on accuracy of the feedforward neural networks so applied was considered. The emphasis was put on neural network's function as state estimator. The choice of the most informative features, the amount and sampling period of training data sets, as well as different configurations of neural networks were analyzed.     

采用神经网络轮胎模型的汽车操纵稳定性仿真

运用人工神经网络理论中的多层前向ＢＰ网络,建立轮胎侧偏特性模型,进而将人工神经网络轮胎代人车模型中进行操纵稳定性仿真研究。     

Interpolation functions of feedforward neural networks

Mathematical essence and structures of the feedforward neural networks are investigated in this paper. The interpolation mechanisms of the feedforward neural networks are explored. For example, the well-known result, namely, that a neural network is an universal approximator, can be concluded naturally from the interpolative representations. Finally, the learning algorithms of the feedforward neural networks are discussed.     

前馈神经网络权值学习的复合形法

本文介绍一种新的前馈神经网络的随机学习方法，着重讨论该算法的实现，并讨论了将它和ＢＰ算法相结合，从而得到一种非常实用的神经网络学习算法。     

基于子空间信息量准则的前向神经网络设计理论与方法研究

从理论上提出了子空间信息量(SIQ)及其准则(SIQC)的概念；在此基础上阐述了基于上述准则的前向神经网络设计的相关理论，包括前向神经网络隐含层信息量(HLIQ)、存在性和逼近定理，给出了选择隐含层神经元数、权值向量集和隐含层激励函数的指导方向；提出了基于上述理论的一种可行的次优网络设计算法；最后，详细分析了网络性能指标及其影响因素，上述理论和方法完全克服了传统学习算法的各种弊端，丰富了前向神经网络设计领域的理论依据，具有较大的理论指导和实际应用价值，文中通过具体实例验证了上述理论和方法的可行性和优越性．     

A new approach to artificial neural networks

A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model with multiple synapses. The synapses' connective strengths are modified through selective and cumulative processes conducted by axo-axonic connections from a feedforward circuit. This new concept was applied to the position control of a planar two-link manipulator exhibiting excellent results on learning capability and generalization when compared with a conventional feedforward network. In the present paper, the example shows only a network developed from a neuronal reflexive circuit with some useful artifices, nevertheless without the intention of covering all possibilities devised.     

A review of genetic algorithms applied to training radial basis function networks

The problems associated with training feedforward artificial neural networks (ANNs) such as the multilayer perceptron (MLP) network and radial basis function (RBF) network have been well documented. The solutions to these problems have inspired a considerable amount of research, one particular area being the application of evolutionary search algorithms such as the genetic algorithm (GA). To date, the vast majority of GA solutions have been aimed at the MLP network. This paper begins with a brief overview of feedforward ANNs and GAs followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.     

Design of neural networks for fast convergence and accuracy:dynamics and control

A procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed, such that once property trained, they provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component/spacecraft design changes and measures of its performance or nonlinear dynamics of the system/components. A training algorithm, based on statistical sampling theory is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The proposed method should work for applications wherein an arbitrary large source of training data can be generated. Two numerical examples are performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.     

The application of a neurocomputer for a control problem

Most artificial neural networks (ANN) are realized on a conventional computer which generally has only one CPU for general routines. In this paper, we used the neurocomputer called MY-NEUPOWER, produced by Hitachi Microcomputer System Ltd., Tokyo, Japan, to carry out research on artificial neural networks. We developed application software for a multilayer feedforward neural network to approximate the nonlinear function of the cooler system in a steel plant. The training algorithm is a type of improved back propagation (BP) algorithm with a variable training coeffcient. The software was programmed on the UNIX platform using the parallel language MY-PARAL. The simulation result demonstrated the merit of the neurocomputer, i.e., the conciseness and simplicity of the program, and the short calculating time. The result also showed that the architecture of neural networks is suitable, and the output error of a neural network is within 5%. This work was presented, in part, at the Third International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–21, 1998     

The truth will come to light: directions and challenges inextracting the knowledge embedded within trained artificial neuralnetworks

To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explanations from feedforward ANN's. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN's but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e,g., recurrent neural networks) and explanation structures. In addition we identify some of the key research questions in extracting the knowledge embedded within ANN's including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results.     

Artificial neural networks controlled fast valving in a powergeneration plant

This paper presents an artificial neural-network-based controller to realize the fast valving in a power generation plant. The backpropagation algorithm is used to train the feedforward neural networks controller. The hardware implementation and the test results of the controller on a physical pilot-scale power plant setup are described in detail. Compared with the conventional fast valving methods applied to the same system, test results both with the computer simulation and on a physical pilot-scale power plant setup demonstrate that the artificial neural network controller has satisfactory generalization capability, reliability, and accuracy to be feasible for this critical control operation.     

一种前馈神经网的快速算法

前馈神经网已经被大量用于非线性信号处理． 经典反向传播算法是一种标准的前馈网络学习算法,但是,对许多应用,反向传播算法的收 敛速度却很慢．本文根据对网络的非线性单元进行线性化而提出一种新的算法,该算法在非 线性信号处理中在精度和收敛速度方面都优于传统的反向传播算法．     

ANN-DT: an algorithm for extraction of decision trees fromartificial neural networks

Although artificial neural networks can represent a variety of complex systems with a high degree of accuracy, these connectionist models are difficult to interpret. This significantly limits the applicability of neural networks in practice, especially where a premium is placed on the comprehensibility or reliability of systems. A novel artificial neural-network decision tree algorithm (ANN-DT) is therefore proposed, which extracts binary decision trees from a trained neural network. The ANN-DT algorithm uses the neural network to generate outputs for samples interpolated from the training data set. In contrast to existing techniques, ANN-DT can extract rules from feedforward neural networks with continuous outputs. These rules are extracted from the neural network without making assumptions about the internal structure of the neural network or the features of the data. A novel attribute selection criterion based on a significance analysis of the variables on the neural-network output is examined. It is shown to have significant benefits in certain cases when compared with the standard criteria of minimum weighted variance over the branches. In three case studies the ANN-DT algorithm compared favorably with CART, a standard decision tree algorithm.     

基于输出误差与偏导数误差信息融合的神经网络训练

文章首先提出了表示前向神经网的泛化能力的一种度量,分析了提高网络泛化能力的主要途径,进而提出了基于网络输出误差与输出对输入偏导数误差信息融合的网络训练策略,给出了两者信息融合的有效方法和相应网络训练算法。具体应用结果表明所提出算法可显著提高网络的泛化能力。     

多层前向小世界神经网络及其函数逼近

借鉴复杂网络的研究成果, 探讨一种在结构上处于规则和随机连接型神经网络之间的网络模型—-多层前向小世界神经网络. 首先对多层前向规则神经网络中的连接依重连概率p进行重连, 构建新的网络模型, 对其特征参数的分析表明, 当0 < p < 1时, 该网络在聚类系数上不同于Watts-Strogatz 模型; 其次用六元组模型对网络进行描述; 最后, 将不同p值下的小世界神经网络用于函数逼近, 仿真结果表明, 当p = 0:1时, 网络具有最优的逼近性能, 收敛性能对比试验也表明, 此时网络在收敛性能、逼近速度等指标上要优于同规模的规则网络和随机网络.