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.     

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。     

Neurocomputing hardware: present and future

This paper discusses the current state of the art of industrial neurocomputing, and then speculates on its future.Three examples of commercial neuro-silicon are presented: the Adaptive Solutions CNAPS system, the Intel ETANN chip, and the Synaptics OCR chip.We then speculate on where commercial neurocomputing hardware is going. In particular we propose that commercial systems will evolve in the direction of capturing more contextual, knowledge level information. Some results of an industrial handwritten character recognition system created at Apple Computers will be presented which demonstrate the power of adding contextual knowledge to neural network based recognition. Also discussed will be some of the possible directions required for neural network algorithms needed to capture such knowledge and utilize it effectively, as well as results from experiments on capturing contextual knowledge using several different neural network algorithms.Finally, the issues involved in designing VLSI architectures for the efficient emulation of sparsely activated, sparsely connected contextual networks will be discussed. There are fundamental cost/performance limits when emulating such sparse structures in both the digital and analog domain.     

人工神经网络技术在超临界流体密度预测中的应用

超临界流体的性质常与其密度相关。因此,如何精确计算超临界流体在不同操作条件下的密度值,对于超临界流体过程的研究和设计均十分重要。本文尝试采用人工神经网络技术来预测计算超临界流体的密度。网络结构为3层BP网,经优化中间隐藏层单元数为6。通过训练和学习,在压力6MPa-8MPa、温度300K-320K范围内,神经网络预测的密度值,其相对误差<0.35％。比P-B状态方程计算的结果精确。     

人工神经元BP网络在股市预测方面的应用

介绍了人工神经元网络在经济领域的应用,主要探讨BerndFreisleben的研究方法,即利用神经BP网络对股票市场股份走势进行预测的方法,重点对利用各种不同网络结构和网络参数所得预测结果进行分析。提出了综合股票历史价格和其他经济因素的精确预测方法。     

BP神经网络在红外CO2体积分数测量中的应用

环境温度对CO2气体体积分数测量的影响是不可忽视的.在CO2体积分数测量中加入温度补偿有助于提高测量装置的精度和有效性,但这很难用传统的数学模型进行温度补偿.反向传播(BP)神经网络特别适用于建立非线性温度补偿网络模型.在实际应用中证明:该方法得到了良好的效果,使CO2气体体积分数测量结果更加准确、稳定.     

Discrete time neural networks

Traditional feedforward neural networks are static structures that simply map input to output. To better reflect the dynamics in the biological system, time dependency is incorporated into the network by using Finite Impulse Response (FIR) linear filters to model the processes of axonal transport, synaptic modulation, and charge dissipation. While a constructive proof gives a theoretical equivalence between the class of problems solvable by the FIR model and the static structure, certain practical and computational advantages exist for the FIR model. Adaptation of the network is achieved through an efficient gradient descent algorithm, which is shown to be a temporal generalization of the popular backpropagation algorithm for static networks. Applications of the network are discussed with a detailed example of using the network for time series prediction.     

一种自适应模糊Petri网及其应用*

模糊Petri网(fuzzy Petri nets, FPN)是基于模糊产生式规则的知识库系统的有力建模工具,但其缺乏较强的自学习能力。在FPN的基础上引入神经网络技术,给出了一种自适应模糊Petri网(adapt fuzzy Petri nets, AFPN)模型。该模型将神经网络中的BP网络算法引入到FPN模型中,对FPN中的权值进行反复的学习训练,避免了依靠人工经验设置带来的不确定性。AFPN具有很强的推理能力和自适应能力,对知识库系统的建立、更新和维护有着重要的意义。     

Predicting grinding burn using artificial neural networks

This paper introduces a method for predicting grinding burn using artificial neural networks (ANN). First, the way to model grinding burn via ANN is presented. Then, as an example, the prediction of grinding burn of ultra-strength steel 300M via ANN is given. Very promising results were obtained.     

Validating a neural network application: The case of financial diagnosis

It has been argued that neural network applications should be benchmarked using several data sets of realistic and real problems, and competing algorithms (Prechelt, 1995). However, if applying a neural network model to a particular real problem is in focus, validation should be considered as a suitability evaluation in which several bases of evaluation are combined in a composite judgment. In this paper, five bases of such evaluation are introduced and applied to the validation of a neural network model of financial diagnosis.     

Trading strategy design in financial investment through a turning points prediction scheme

Turning points prediction has long been a tough task in the field of time series analysis due to its strong nonlinearity, and thus has attracted many research efforts. In this study, the turning points prediction (TPP) framework is presented and further employed to develop a novel trading strategy designing approach to financial investment. The TPP framework is a machine learning-based solution incorporating chaotic dynamic analysis and neural network modeling. It works on the ground of a nonlinear mapping deduced in financial time series through chaotic analysis. An event characterization method is created in TTP framework to characterize trend patterns in ongoing financial time series. The main contributions of this paper are (1) it presents an ensemble learning based TPP framework, within which the nonlinear mapping is approximated by the ensemble artificial neural network (EANN) model with a new parameters learning algorithm; (2) a genetic algorithm (GA) based threshold optimization procedure is described with a newly defined performance measure, named TpMSE, which is used as a cost function; and (3) a trading strategy designing approach is proposed based on the TPP framework. The proposed approach was applied to the two real-world financial time series, i.e., an individual stock quote time series and the Dow Jones Industrial Average (DJIA) index time series. Experimental results show that the proposed approach can help investors make profitable decisions.     

Distributed routing in packet-switching networks by counterpropagation network

Routing is a problem of considerable importance in a packet-switching network, because it allows both optimization of the transmission speeds available and minimization of the time required to deliver information. In classical centralized routing algorithms, each packet reaches its destination along the shortest path, although some network bandwidth is lost through overheads. By contrast, distributed routing algorithms usually limit the overloading of transmission links, but they cannot guarantee optimization of the paths between source and destination nodes on account of the mainly local vision they have of the problem. The aim of the authors is to reconcile the two advantages of classical routing strategies mentioned above through the use of neural networks. The approach proposed here is one in which the routing strategy guarantees the delivery of information along almost optimal paths, but distributes calculation to the various switching nodes. The article assesses the performance of this approach in terms of both routing paths and efficiency in bandwidth use, through comparison with classical approaches.     

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.     

Evolving modular networks with genetic algorithms: application to nonlinear time series

Abstract: A key problem of modular neural networks is finding the optimal aggregation of the different subtasks (or modules) of the problem at hand. Functional networks provide a partial solution to this problem, since the inter‐module topology is obtained from domain knowledge (functional relationships and symmetries). However, the learning process may be too restrictive in some situations, since the resulting modules (functional units) are assumed to be linear combinations of selected families of functions. In this paper, we present a non‐parametric learning approach for functional networks using feedforward neural networks for approximating the functional modules of the resulting architecture; we also introduce a genetic algorithm for finding the optimal intra‐module topology (the appropriate balance of neurons for the different modules according to the complexity of their respective tasks). Some benchmark examples from nonlinear time‐series prediction are used to illustrate the performance of the algorithm for finding optimal modular network architectures for specific problems.     

Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference

Financial forecasting is an example of a signal processing problem which is challenging due to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been very successful in a number of signal processing applications. We discuss fundamental limitations and inherent difficulties when using neural networks for the processing of high noise, small sample size signals. We introduce a new intelligent signal processing method which addresses the difficulties. The method proposed uses conversion into a symbolic representation with a self-organizing map, and grammatical inference with recurrent neural networks. We apply the method to the prediction of daily foreign exchange rates, addressing difficulties with non-stationarity, overfitting, and unequal a priori class probabilities, and we find significant predictability in comprehensive experiments covering 5 different foreign exchange rates. The method correctly predicts the directionof change for the next day with an error rate of 47.1%. The error rate reduces to around 40% when rejecting examples where the system has low confidence in its prediction. We show that the symbolic representation aids the extraction of symbolic knowledge from the trained recurrent neural networks in the form of deterministic finite state automata. These automata explain the operation of the system and are often relatively simple. Automata rules related to well known behavior such as tr end following and mean reversal are extracted.     

Multi-step Learning Rule for Recurrent Neural Models: An Application to Time Series Forecasting

Multi-step prediction is a difficult task that has attracted increasing interest in recent years. It tries to achieve predictions several steps ahead into the future starting from current information. The interest in this work is the development of nonlinear neural models for the purpose of building multi-step time series prediction schemes. In that context, the most popular neural models are based on the traditional feedforward neural networks. However, this kind of model may present some disadvantages when a long-term prediction problem is formulated because they are trained to predict only the next sampling time. In this paper, a neural model based on a partially recurrent neural network is proposed as a better alternative. For the recurrent model, a learning phase with the purpose of long-term prediction is imposed, which allows to obtain better predictions of time series in the future. In order to validate the performance of the recurrent neural model to predict the dynamic behaviour of the series in the future, three different data time series have been used as study cases. An artificial data time series, the logistic map, and two real time series, sunspots and laser data. Models based on feedforward neural networks have also been used and compared against the proposed model. The results suggest than the recurrent model can help in improving the prediction accuracy.     

Bayesian selective combination of multiple neural networks for improving long-range predictions in nonlinear process modelling

A Bayesian selective combination method is proposed for combining multiple neural networks in nonlinear dynamic process modelling. Instead of using fixed combination weights, the probability of a particular network being the true model is used as the combination weight for combining that network. The prior probability is calculated using the sum of squared errors of individual networks on a sliding window covering the most recent sampling times. A nearest neighbour method is used for estimating the network error for a given input data point, which is then used in calculating the combination weights for individual networks. Forward selection and backward elimination are used to select the individual networks to be combined. In forward selection, individual networks are gradually added into the aggregated network until the aggregated network error on the original training and testing data sets cannot be further reduced. In backward elimination, all the individual networks are initially aggregated and some of the individual networks are then gradually eliminated until the aggregated network error on the original training and testing data sets cannot be further reduced. Application results demonstrate that the proposed techniques can significantly improve model generalisation and perform better than aggregating all the individual networks.     

Fault Diagnosis Based on the Fuzzy‐Recurrent Neural Network

A fuzzy‐recurrent neural network (FRNN) has been constructed by adding some feedback connections to a feedforward fuzzy neural network (FNN). The FRNN expands the modeling ability of a FNN in order to deal with temporal problems. A basic concept of the FRNN is first to use process or expert knowledge, including appropriate fuzzy logic rules and membership functions, to construct an initial structure and to then use parameter‐learning algorithms to fine‐tune the membership functions and other parameters. Its recurrent property makes it suitable for dealing with temporal problems, such as on‐line fault diagnosis. In addition, it also provides human‐understandable meaning to the normal feedforward multilayer neural network, in which the internal units are always opaque to users. In a word, the trained FRNN has good interpreting ability and one‐step‐ahead predicting ability. To demonstrate the performance of the FRNN in diagnosis, a comparison is made with a conventional feedforward network. The efficiency of the FRNN is verified by the results.