污水处理中BP神经网络与Elman神经网络的预测比较

以活性污泥污水处理过程为背景,介绍并比较了BP神经网络与Elman神经网络对于污水处理输出化学需氧量(COD)的预测.实验结果表明,Elman神经网络训练时间要比BP神经网络训练时间长,但是Elman神经网络预测的精确度要比BP神经网络预测的精确度高,Elman神经网络能够更好的预测污水处理的进程.     

Implementing probabilistic Neural Networks

A modified PNN training algorithm is proposed. The standard PNN, though requiring a very short training time, when implemented in hardware exhibits the drawbacks of being costly in terms of classification time and of requiring an unlimited number of units. The proposed modification overcomes the latter drawback by introducing an elimination criterion to avoid the storage of unnecessary patterns. The distortion in the density estimation introduced by this criterion is compensated for by a crossvalidation procedure to adapt the network parameters. The present paper deals with a specific realworld application, i.e. handwritten character classification. The proposed algorithm makes it possible to realise the PNN in hardware and, at the same time, compensates for some inadequacies arising from the theoretical basis of the PNN, which does not perform well with small training sets.     

随机Hopfiedld神经网络的稳定性分析

通过利用动态大规模互连系统的分解方法,对由Ｉｔｏ随机微分方程描述的随机Ｈｏｐｆｉｌｅｄ神经网络给出了稳定性分析,这样的神经网络被认为是许多神经元的一个互连,在本文中给出了稳定性结论是以单个神经凶和互连结构的性质来表示的。     

模糊系统和神经网络的特征与比较

概述了模糊、神经网络 和人工智能技术之间的关系，尤其探讨了模糊系统和神经网络的特性；指出了模糊系统和神经网络的结合方式，分析了它们的特征。     

Experiments of Trust Prediction in Social Networks by Artificial Neural Networks

Social network online services are growing at an exponential pace, both in quantity of users and diversity of services; thus, the evaluation of trust in the interaction among users and toward the system is a central issue from the user point of view. Trust can be grounded in past direct experience or in the indirect information provided by trusted third-party users shaping the trustee reputation. When there is no previous history of interactions, the truster must resort to some form of prediction in order to establish Trust or Distrust on a potential trustee. In this study, we deal with the prediction of trust relationships on the basis of reputation information. Trust can be positive or negative (Distrust), hence, we have a two-class problem. Feature vectors for the classification have binary-valued components. Artificial neural network and statistical classifiers provide state-of-the-art results with these features on a benchmarking trust database. In this article, we propose the application of a sample generation method for the minority class in order to reduce some of the effect of class imbalance among Trust and Distrust classes. Specifically, the approach shows high resiliency to system growth.     

基于随机游走的带有属性网络的链接预测

链接预测的问题是复杂网络分析中的一个重要研究领域,已经在社会学、生物信息学、信息科学以及计算机科学等领域得到了广泛的应用。提出了一个顶点具有属性的网络链接预测的随机游走算法。在此算法中,根据顶点和属性的链接相似度定义了每一条边上的传播概率。并将顶点的属性相似度作为顶点间的相似度的初值,然后根据传输概率在网络中以随机游走的方式进行传播和更新,最终得到顶点间的相似度作为链接预测的结果得分。实验结果显示,提出的算法在顶点带属性的网络中取得了比其他算法更精确的预测结果。     

基于级联神经网络的蛋白质二级结构预测

为提高蛋白质二级结构预测的精度,提出一种由两层网络构成的级联神经网络模型。第1层网络采用具有差异度的5个子网构成的网络模型,对第2层网络的输入编码进行改进。对PDBSelect25中的36条蛋白质共6 122个残基进行测试,结果表明,该模型能有效预测蛋白质二级结构,其预测精度分别比SNN, DSC, PREDSATOR方法提高5.31%, 1.21%和0.92%,平均预测精度提高到69.61%。     

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.     

Online Text Prediction with Recurrent Neural Networks

Arithmetic coding is one of the most outstanding techniques for lossless data compression. It attains its good performance with the help of a probability model which indicates at each step the probability of occurrence of each possible input symbol given the current context. The better this model, the greater the compression ratio achieved. This work analyses the use of discrete-time recurrent neural networks and their capability for predicting the next symbol in a sequence in order to implement that model. The focus of this study is on online prediction, a task much harder than the classical offline grammatical inference with neural networks. The results obtained show that recurrent neural networks have no problem when the sequences come from the output of a finite-state machine, easily giving high compression ratios. When compressing real texts, however, the dynamics of the sequences seem to be too complex to be learned online correctly by the net.     

Sparse algorithms of Random Weight Networks and applications

This paper studies sparse algorithms for training Random Weight Networks (RWN) and their applications. The proposed algorithms contain three principal steps: initialization of networks structure, simplification of RWN structure based on sparse coding, and relearning process with renewed nodes. A key of the algorithms is sparse coding of hidden layer neurons by adding an initialization process to simplify the networks structure. Specially, the new algorithms, to some extent, can avoid the over-fitting phenomenon efficiently. As applications, the algorithms are used to diagnose the fault of switch reluctance motor (SRM) and to recognize the human face. Compared with the traditional back-propagation (BP) and RWN algorithms, the experimental results show that the proposed algorithms have effective performances on the accuracy or time. These methodologies can also be conceived as support tools for the practical fault diagnosis of SRM and the human face pattern recognition.