Neural networks and their applications in component design data retrieval

Neural networks have gained increased importance in the past few years. One of the basic characteristics of neural networks is the property of associative memory. In this paper we study the possibility of using the ideas of neural networks and associative memory in the manufacturing domain, with specific reference to design data retrieval in group technology. A two-layer feed-forward perceptron with backpropagation is simulated on a Vax-8550 to train example parts. The complete scheme along with the simulation results are explained and future directions indicated.     

Chaotic properties and pattern competition during the learning phase of back propagation neural networks

This paper examines the chaotic behavior of Back Propagation neural networks during the training phase. The networks are trained using ordinary parameter values, while two different cases are considered. In the first one, the network does not meet desirable convergence within a pre-specified number of epochs. Chaotic behavior of this network is depicted by examining the values of the dominant Lyapunov exponents of the weight data series produced by additional training. For each training epoch, the data series representing input patterns producing the minimum absolute error in output during additional training, is also subjected to Lyapunov exponent investigation. The task of this investigation is to determine whether the network exhibits chaotic pattern competition of the best learned inputs. In the second case, the network is improved and desirable convergence is accomplished. Again, investigation focuses on the series of values representing input patterns that produce outputs with minimum absolute error. The results obtained from dominant Lyapunov exponent estimations show that chaotic pattern competition is still present, despite the fact that the network practically satisfies stability demands within predetermined accuracy limits. The best estimation series consist of the output values corresponding to the best learned input patterns. These series are examined using the theoretical tool of topological conjugacy, in addition to numerical verification of the results.     

Servo controller design using neural networks

The dynamics of a physical plant may be difficult to express as concise mathematical equations. In practice there exist uncertainties that cannot be modeled with the system equations. Hence, robustness against system uncertainties is essential in a control system design. In this article, multilayered neural networks (MNNs) are used to compensate for model uncertainties of a dynamical system. Neural network models are used along with a classical linear servo controller derived from the linear state space equations. These models are trained so that system uncertainties are compensated. The design of a servo system indicates the enhanced performance of the neural-network-based servo controller as compared to the classical servo controller.     

基于神经网络和模式匹配的股票预测研究

BP神经网络是分析股票数据最流行的工具之一。近期对模式匹配算法的研究表明模式匹配简化了股票趋势预测的复杂度并为股票市场预测提供了一种简单有效的方法。文中分别阐述了BP神经网络和模式匹配识别的原理,并提出将两种算法相结合,建立一个基于BP神经网络和模式匹配识别的股票市场分析和预测系统。这个系统克服了神经网络预测系统目标函数存在局部最小和模式匹配识别预测系统缺少股票价格自身变化特性的缺点,具有两种算法在股票预测应用方面的优势。通过对泰山石油的股价进行分析来测试这个系统。实验结果表明此方法不仅收敛速度快、预测精度高,而且易于操作,具有一定应用价值。     

Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories.

In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught?

If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory.

This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.     

Artificial neural networks and bankruptcy forecasting: a state of the art

The use of neural networks in finance began by the end of the 1980s and by the beginning of the 1990s, it developed specific applications related to forecasting on the failure of companies. In order to highlight the evolution of this research stream, we have retained and analysed 30 studies in which the authors use neural networks to solve companies’ classification problems (healthy and failing firms). This review of all these works gives us the opportunity to stress upon future trends in bankruptcy forecasting research.

Neural networks in robotics: A survey

The purpose of this paper is to provide an overview of the research being done in neural network approaches to robotics, outline the strengths and weaknesses of current approaches, and predict future trends in this area.This work was supported, in part, by Sandia National Laboratories under contract No. 06-1977, Albuquerque, New Mexico.     

Neural networks in virtual reference tuning

This paper discusses the application of the virtual reference tuning (VRT) techniques to tune neural controllers from batch input-output data, by particularising nonlinear VRT and suitably computing gradients backpropagating in time. The flexibility of gradient computation with neural networks also allows alternative block diagrams with extra inputs to be considered. The neural approach to VRT in a closed-loop setup is compared to the linear VRFT one in a simulated crane example.     

The use of data mining and neural networks for forecasting stock market returns

It has been widely accepted by many studies that non-linearity exists in the financial markets and that neural networks can be effectively used to uncover this relationship. Unfortunately, many of these studies fail to consider alternative forecasting techniques, the relevance of input variables, or the performance of the models when using different trading strategies. This paper introduces an information gain technique used in machine learning for data mining to evaluate the predictive relationships of numerous financial and economic variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. A cross-validation technique is also employed to improve the generalization ability of several models. The results show that the trading strategies guided by the classification models generate higher risk-adjusted profits than the buy-and-hold strategy, as well as those guided by the level-estimation based forecasts of the neural network and linear regression models.     

融合宽残差和长短时记忆网络的动态手势识别研究

针对现有的动态手势识别方法对长时间序列的时空特征难以精确匹配的问题,提出了一种基于宽残差和双向长短时记忆网络的时空特征一致手势识别方法。首先使用已经训练好的3D卷积神经网络从视频的空间和时间维度同步提取出短时特征,再经双向空间长短时记忆网络同步解析后形成长时空特征连接单元,并作为残差网络的输入。为了验证算法的有效性,使用Kinect传感器构建了一个全新的多模式手势数据集,在三个手势识别公开数据集SLVM、Montalbano和SKIG上的实验表明,提出的方法有很好的性能表现,识别精度超越了目前已公开的最佳识别率。     

Multiple neural networks for a long term time series forecast

The artificial neural network (ANN) methodology has been used in various time series prediction applications. However, the accuracy of a neural network model may be seriously compromised when it is used recursively for making long-term multi-step predictions. This study presents a method using multiple ANNs to make a long term time series prediction. A multiple neural network (MNN) model is a group of neural networks that work together to solve a problem. In the proposed MNN approach, each component neural network makes forecasts at a different length of time ahead. The MNN method was applied to the problem of forecasting an hourly customer demand for gas at a compression station in Saskatchewan, Canada. The results showed that a MNN model performed better than a single ANN model for long term prediction.

基于差分理论的短期负荷预测神经网络模型

电力负荷是受周期性变化以及天气等因素影响的高度非线性系统,而神经网络仅仅对已学习过的模式具有较好的范化能力。为提高神经网络的负荷预测精度,提出先对原始负荷序列进行差分运算以除去其周期性影响,然后依据相似性原理建立RBF神经网络预测模型,仿真实验表明采用该方法短期负荷预测精度有所改善。     

Neural-network process modeling of a continuous manufacturing operation

Neural-network techniques for the development of models of critical parameters in continuous forest products manufacturing processes are described. Predictive models of strength parameters in particleboard manufacturing were developed utilizing both backpropagation and counterpropagation neural network techniques. The modeled strength parameters were modulus of rupture and internal bond. The backpropagation neural network model did not provide sufficient accuracy in predicting the values of the strength parameters. Counterpropagation was successful at predicting modulus of rupture within ± 10% and internal bond within ± 15%. The trained counterpropagation network can be used to improve process control and reduce the amount of substandard and scrap board produced. Efforts are underway to refine the counterpropagation network and further improve its predictive capability, as well as to evaluate alternative neural network paradigms.     

Neural networks,rational functions,and realization theory

The problem of parametrizing single hidden layer scalar neural networks with continuous activation functions is investigated. A connection is drawn between realization theory for linear dynamical systems, rational functions, and neural networks that appears to be new. A result of this connection is a general parametrization of such neural networks in terms of strictly proper rational functions. Some existence and uniqueness results are derived. Jordan decompositions are developed, which show how the general form can be expressed in terms of a sum of canonical second order sections. The parametrization may be useful for studying learning algorithms.This work was supported by the Australian Research Council, the Australian Telecommunications and Electronics Research Board, and the Boeing Commencai Aircraft Company (thanks to John Moore).     

Multi-class pattern classification using neural networks

Multi-class pattern classification has many applications including text document classification, speech recognition, object recognition, etc. Multi-class pattern classification using neural networks is not a trivial extension from two-class neural networks. This paper presents a comprehensive and competitive study in multi-class neural learning with focuses on issues including neural network architecture, encoding schemes, training methodology and training time complexity. Our study includes multi-class pattern classification using either a system of multiple neural networks or a single neural network, and modeling pattern classes using one-against-all, one-against-one, one-against-higher-order, and P-against-Q. We also discuss implementations of these approaches and analyze training time complexity associated with each approach. We evaluate six different neural network system architectures for multi-class pattern classification along the dimensions of imbalanced data, large number of pattern classes, large vs. small training data through experiments conducted on well-known benchmark data.     

BP神经网络及其在数据分类中的应用

BP神经网络模型是一种典型的前向型神经网络,具有良好的自学习、自适应、联想记忆、并行处理和非线形转换的能力,是目前应用最为广泛的一种神经网络模型。本文介绍了BP神经网络的实现以及其在数据挖掘分类方面的应用。     

Neural networks in quality function deployment

Quality Function Deployment (QFD) is a method of product planning in the early phases of the development of new products (pre-CAD phase). A major drawback of its application is the need to input a large amount of data and the necessity to estimate values on a rather subjective basis in order to complete the House of Quality. This data is plentiful and often designers lack the knowledge with satisfying accuracy. This paper suggests a machine learning approach in which a neural network automatically determines the data by learning from examples. Unlike conventional neural networks which are treated as black boxes, the topology and the weight values are not random but represent real circumstances and can directly be interpreted in the terms of the application. A final section discusses problems arising from the small number of training sets which is usually available in the field of product design.     

基于神经网络的负荷预测仿真研究

提高电力负荷预测精度有利于电力部门的安全生产,有利于合理安排电网运行方式和机组的检修计划,有利于系统的合理规划和经济运行。为了提高短期负荷预测的精度,把自相关函数的概念应用到反向传播(Back Propogation,BP)神经网络输入变量选择中,通过MATLAB仿真软件建立负荷预测模型。最后对某电力系统1d的负荷进行预测,仿真结果验证了该模型的可行性和有效性。     

变窗口神经网络集成预测模型*

针对时间序列问题,提出了一个变窗口神经网络集成预测模型。利用自相关分析方法挖掘时间序列本身蕴涵的变化特性,并利用这些变化特性构造差异度较大的个体神经网络。变窗口集成预测模型在应用于时间序列预测的同时,还可以有效地对异常序列进行筛选和分离。将该模型应用于移动通信话务量的预测。实验分析表明,该预测系统具有较高的预测精度,并能有效地对异常序列进行分离。     

Neural network modelling of continuous microbial cultivation accounting for the memory effects

Three approaches to the problem of Neural Network (NN) modelling of chemostat microbial culture accounting for the memory effects are considered and, based on the results they are compared. The first approach uses feedforward NNs with time delay feedback connections from and to the output neurons, for the entire process modelling. The second and third approach relay on Hybrid NN modelling. The second one applies feedforward NNs with time delayed inputs for the specific growth rate approximation within the framework of the classical unstructured model. In this case the specific consumption rate is assumed to be proportional to the specific growth rate. The yield factor is assumed to be constant or polynomial function of the substrate concentration. The third approach is also based on a classical unstructured model, but different feedforward NNs with delay elements for both specific growth rate and specific consumption rate approximation are adopted. On the example of the growth of a strain Saccharomyces cerevisiae on a glucose limited medium different NN topologies are studied and a suitable model is figured out.