激光水下成像技术及其进展

介绍了近年发展起来的三种主要的激光水下成像方法，即常规水下激光成像、高分辨率水下激光三维成像和偏振激光成像，分析了它们各自的工作原理、特点以及各自的发展状况。     

基于主成分分析的输出集成反馈网络及其在化工动态过程建模中的应用

针对主成分分析和反馈神经网络的优点，提出基于主成分分析的输出集成反馈网络建模方法，并对训练算法作了推导，在动态化工过程建模中取得满意的效果。     

高属性维稀疏数据聚类回归逻辑 神经网络模型及学习算法

针对高属性维稀疏数据聚类问题,定义了模糊取大逻辑神经元,给出一种新的单层离散型回归逻辑神经网络模型,由稀疏特征差异度组成的相似阵作为该网络的初始权矩阵,通过单层离散型回归逻辑神经网络学习算法,可求出相似矩阵的等价阵,根据等价阵,给定不同的阈值,可动态地、有效地实现对高属性维稀疏数据的归并,使得聚类结果更符合实际情况,聚类质量较高.相比同类聚类算法,它具有学习、修正和应变功能,适用于大规模稀疏数据库和稀疏数据仓库的聚类分析.     

Learn more by training less: systematicity in sentence processing by recurrent networks

Connectionist models of sentence processing must learn to behave systematically by generalizing from a small training set. To what extent recurrent neural networks manage this generalization task is investigated. In contrast to Van der Velde et al. (Connection Sci., 16, pp. 21–46, 2004), it is found that simple recurrent networks do show so-called weak combinatorial systematicity, although their performance remains limited. It is argued that these limitations arise from overfitting in large networks. Generalization can be improved by increasing the size of the recurrent layer without training its connections, thereby combining a large short-term memory with a small long-term memory capacity. Performance can be improved further by increasing the number of word types in the training set.     

Modeling heterogeneity in social interaction processes using multilevel survival analysis.

More than 15 years ago, survival or hazard regression analyses were introduced to psychology (W. Gardner & W. A. Griffin, 1989; W. A. Griffin & W. Gardner, 1989) as powerful methodological tools for studying real time social interaction processes among dyads. Almost no additional published applications have appeared, although such data are commonly collected and the applicable questions are central to many important theoretical perspectives. To revisit the basic methods, the authors use an example from emotion regulation theory in which the level of child antisocial behavior is hypothesized to be positively associated with the hazard rate of angry emotions and negatively associated with sad, fearful emotions in the face of parental negative behavior (scolding). The authors discuss the limitations of traditional approaches to the analysis of social interaction and demonstrate improvements in the ability to model individual differences now available in existing software. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Context-gated knowledge partitioning in categorization.

According to the knowledge partitioning framework, people sometimes master complex tasks by creating multiple independent parcels of partial knowledge. Research has shown that knowledge parcels may contain mutually contradictory information, and that each parcel may be used without regard to knowledge that is demonstrably present in other parcels. This article reports 4 experiments that investigated knowledge partitioning in categorization. When component boundaries of a complex categorization were identified by a context cue, a significant proportion of participants learned partial and independent categorization strategies that were chosen on the basis of context. For those participants, a strategy used in one context was unaffected by knowledge demonstrably present in other contexts, suggesting that knowledge partitioning in categorization can be complete. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Packet Delay Analysis of Symmetric Gated Polling System for DBA Scheme in an EPON

In this paper, we analyze the mean packet delay of a dynamic bandwidth allocation (DBA) scheme in an Ethernet passive optical network (EPON). We propose the interleaved polling system with a gated service discipline and a two-stage queue in order to investigate the delay performance of DBA scheme in an EPON. We assume that input packets arrive at an optical network unit (ONU) according to a Poisson process from several types of users. We use a continuous time queueing model in order to find the mean packet delay and the mean cycle time of an arbitrary packet. We obtain the closed form solution for the mean packet delay of the proposed gated polling system with a two-stage queue. We obtain another result on the mean packet delay by solving a system of linear equations derived from the moments of the queue length distribution. We give some numerical results to investigate the delay performances for the symmetric polling system with statistically identical stations. In addition, we compare numerical results on the closed form solution with numerical results on a system of linear equations.     

制糖过程中递归模糊神经网络软测量技术

糖厂澄清工段过程包含复杂的物理和化学反应,具有非线性、大滞后和不确定性的特点,难以建立精确的机理模型.常规神经网络建模是静态映射,实际应用中,权值的调节不能充分利用工业生产现场的动态数据信息,效果不理想.为此,提出了含有递归环节的T-S模糊神经网络(TSRFNN)结构,采用混沌BP学习算法引入非线性自反馈项获得复杂系统的动力学特征,通过与常规T-S模糊神经网络(TSFNN)在糖厂澄清工段过程的建模与仿真试验中进行比较,结果表明,在处理这类时变复杂系统建模方面TSRFNN表现出更加优越的性能,获得了非线性系统的全局最优模型.     

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.     

基于神经网络的传感器冗余方法研究􀀁

本文把传感器硬件冗余技术、BP网络以及串并联Elman递归神经网络结合起来,提出了一种新方法用于构造具有传感器故障检测、分离且具有冗余能力的智能传感器系统。这可以减少硬件冗余技术中使用传感器的个数、消除硬件冗余技术中对冗余传感器应具有相同参数特性的要求,同时可以提高系统预报的准确性,仿真结果验证了这一方法的有效性。