纳秒量级门控积分器的初步研究

在ＩＣＦ软Ｘ射线能量测量时，需要对纳秒量级的脉冲信号积分，但是脉冲信号后伴随其他信号，而目前的线性开关电路或门控积分器又无法在纳秒量级内将脉冲信号后的部分切除，本文介绍了一种新型的纳秒量级门控积分器，能够实现纳秒量级的门控积分。     

连通图临界度定义的注记

本文递归地定义了连通图的临界度,并证明了几个定理,揭示了连通图临界度的特殊性质,说明所给出的递归定义与常规定义之间的关系.     

Recurrent neural networks and prior knowledge for sequence processing: a constrained nondeterministic approach

The paper focuses on methods for injecting prior knowledge into adaptive recurrent networks for sequence processing. In order to increase the flexibility needed for specifying partially known rules, a nondeterministic approach for modelling domain knowledge is proposed. The algorithms presented in the paper allow time-warping nondeterministic automata to be mapped into recurrent architectures with first-order connections. These kinds of automata are suitable for modeling temporal scale distortions in data such as acoustic sequences occurring in problems of speech recognition. The algorithms output a recurrent architecture and a feasible region in the connection weight space. It is demonstrated that, as long as the weights are constrained into the feasible region, the nondeterministic rules introduced using prior knowledge are not destroyed by learning. The paper focuses primarily on architectural issues, but the proposed method allows the connection weights to be subsequently tuned to adapt the behavior of the network to data.     

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。     

Recurrent Schemes for Generating and Choosing Alternatives of Systems Based on Operational Models

Recurrent schemes for generating alternatives of systems by given scalable operational models are proposed and substantiated. Recurrent schemes represent tools for generating alternatives based on structural and parametric transformations of operational models. Existence conditions for the solution to the generation and choice problem and the convergence of the recurrent scheme are analyzed and model examples are discussed.     

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)     

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.     

复合栅控二极管新技术提取热载流子诱生的NMOS/SOI器件界面陷阱的横向分布

提出了用复合栅控二极管新技术提取MOS/SOI器件界面陷阱沿沟道横向分布的原理,给出了具体的测试步骤和方法.在此基础上,对具有体接触的NMOS/SOI器件进行了具体的测试和分析,给出了不同的累积应力时间下的界面陷阱沿沟道方向的横向分布.结果表明:随累积应力时间的增加,不仅漏端边界的界面陷阱峰值上升,而且沿沟道方向,界面陷阱从漏端不断向源端增生.     

Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.