从示例中获取结构化描述的知识—过程

文章提出了适合结构化知识获取的一种思想方法，并结合在种简明而典型的应用领域内实现的过程获取系统ＫＢＭＬ，详细地阐述了这种思想的有关方面。它采用分级分阶段的匹配、归纳策略略逐步从示教实例中获取一个完整的过程；把匹配和归纳有机地结合在一起是ＫＢＭＬ的核心内容。     

基于BP网络的色彩匹配方法研究

提出了一种基于ＢＰ网络的色彩匹配方法,它既解决了ＲＧＢ色彩空间到ＣＭＹＫ色彩空间的非线性转换关系,又可用于其它的色彩空间转换,首先,给出样本数据的选取和转换方案,并结合色彩匹配的特点,利用迭代组织数据分析算法实现对样本数据的动态聚类,其次,在将ＢＰ网络用于色彩匹配的过程中,设计了合理的网络结构,并对训练数据进行了规格化处理,最后,讨论了网络训练及测试情况以及在打印应用中的效果。     

一种基于二叉树的元知识学习算法MKL及其应用

ＭＫＬ是知识获取系统ＮＤＫＡＳ中实现的一个元知识学习算法，它在分类及抽象的基础上归纳出二叉树结构的元知识，用以有效地组织知识库中的规则．ＭＫＬ生成的元知识满足元知识的基本性质．本文给出了ＭＫＬ的算法描述，基本性质的满足性证明及算法的应用例子．     

基于MATLAB（SIMULINK）的模糊控制系统计算机仿真

将ＭＡＴＬＡＢ的ＦＵＺＺＹ ＴＯＯＬＢＯＸ中的模糊推理系统（Ｆｕｚｚｙ Ｉｎｔｅｒｅｎｃｅ Ｓｙｓｔｅｍ）编辑器与ＳＩＭＵＬＩＮＫ有机结合起来,充分利用它们各自的优势,方便地实现了模糊控制系统（ＦＣＳ）的计算机仿真。从而克服了对复杂控制律无法直接应用ＳＩＭＵＬＩＮＫ进行仿真的缺点,了ＳＩＭＵＬＩＮＫ的应用范围。     

支持MPEG—2的ME芯片的结构设计

基于全搜索块匹配算法（ＦｕｌＳｅａｒｃｈＢｌｏｃｋＭａｔｃｈｉｎｇＡｌｇｏｒｉｔｈｍ简称ＦＢＭＡ），提出一种支持ＭＰＥＧ－２综合运动估计的面向ＶＬＳＩ实现的心动阵列结构，它作为Ｔ．Ｋｏｍａｒｅｋ的ＡＢ２结构的一种变形，继承了心动阵列易于扩充运算规模的优点，同时降低了局存与运算阵列之间的数据宽度。另外，为了支持ＭＰＥＧ－２对运动估计的扩充要求，这种结构可以在得到１６×１６块匹配结果的同时，得到两个１６×８场块的匹配结果。最后，从局部存储器的设计和控制器的工作流程分析说明，这种结构在工程上是易于实现的。     

多媒体应用开发工具——TOOLBOOK3.0中的动画制作与播放

本文系统归纳总结了典型多媒体应用开发工具ＴＯＯＬＢＯＯＫ的主要动画制作方法和技巧，较详细地论述了怎样在ＴＯＯＬＢＯＯＫ中播放由其它动画软件生成的ＦＬＣ．ＦＬＩ动画文件；系统地介绍了在ＴＯＯＬＢＯＯＫ中实现动画与声音关联方法以及ＷｉｎｄｏｗｓＡＰＩ函数的调用方法，旨在开发多媒体应用软件提供捷径。     

KBASE—P：一个知识库程序设计语言

ＫＢＡＳＥ－Ｐ是一个知识库程序设计语言，它以ＫＢＡＳＥ作为查询语言，以ＦＤ－ＰＲＯＬＯＧ为过程性的宿主语言，二者具有要同的编程风范，都是Ｈｏｒｎ子句风范，并且系统对任何磁盘访问是以“每次一个集合”的方式进行，因此在ＫＢＡＳＥ－Ｐ中，查询语言与宿主语言之间的“阻抗不匹配”问题尽可能地减小了，ＫＢＡＳＥ－Ｐ以ＲＤＢＭＳ来管理事实（包括中间求值结果）和规则，因此能够有效地管理大容量的数据，并且数据是可菜     

具有面向对象特征和知识库系统

本文讨论了具有面向对象特征的知识库系统ＫＢＡＳＥ＾＋的数据模型，语言及实现。ＫＢＡＳＥ＾＋的数据模型可可以方便地支持对象标识，类层次，多继承等面和对象概念。描述性查询语言ＫＢＬ是ＤＡＴＡＬＯＧ针对于非一范式关系模型的扩充。本文重构了ＫＢＬ的语义理论框架，提出了通过计算相关的下确界来解决属性继承中的冲突问题，通过在ＫＢＬ程序中添加规则来实现实例继承的方案。本文说明了ＫＢＬ程序可以转换成语义等价的ＤＡ     

KBASE—P知识库系统的设计与实现

当前的实用知识库系统研究是将知识库查询语言嵌入到一个过程语言中。ＫＢＡＳＥ－Ｐ是一个通用的知识库程序设计语言。ＫＢＡＳＥ－Ｐ以ＫＢＡＳＥ作为查询语言，以ＦＤ－ＰＲＯＬＯＧ（我们开发的一个ＰＲＯＬＯＧ扩充）为过程性的宿主语言执行Ｉ／Ｏ和ＤＢ更新操作（用扩充的内部谓词）。由于良好的设计和实现，查询语言与宿主语言之间的阻抗不匹配问题相对较小。因而，ＫＢＡＳＥ－Ｐ是一个比较实用的知识库程序设计语言。ＫＢＡ     

Intel Itamium处理器的Cache

Ｉｎｔｅｌ最近更新了关于第一款ＩＡ－６４体系微架构的Ｉｔａｎｉｕｍ处理器的新特点,这款６４ｂｉｔ　Ｉｔａｎｉｕｍ处理器采用有限的Ｌ２－Ｃａｃｈｅ,只有９６ＫＢ,双Ｌ１－Ｃａｃｈｅ将分别为１６ＫＢ,另外,Ｉｔａｎｉｕｍ还拥有一个非常快的１２８位结构Ｌ３－Ｃａｃｈｅ,容量可达２－４ＭＢ,而Ｉｔａｎｉｕｍ的升级版本ＭｃＫｉｎｌｅｙ则拥有更大的Ｌ１和Ｌ２－Ｃａｃｈｅ。 下面是ＩｔａｎｉｕｍＣａｃｈｅ的细节情况： Ｌ１－Ｃａｃｈｅ容量为１６Ｋｂｙｔｅ,采用３２ｂｙｔｅ管线４路（４－ｗａｙ）联合指令; 统一Ｌ…     

Three-valued completion for abductive logic programs

In this paper, we propose a three-valued completion semantics for abductive logic programs, which solves some problems associated with the Console et al. two-valued completion semantics. The semantics is a generalization of Kunen's completion semantics for general logic programs, which is known to correspond very well to a class of effective proof procedures for general logic programs. Secondly, we propose a proof procedure for abductive logic programs, which is a generalization of a proof procedure for general logic programs based on constructive negation. This proof procedure is sound and complete with respect to the proposed semantics. By generalizing a number of results on general logic programs to the class of abductive logic programs, we present further evidence for the idea that limited forms of abduction can be added quite naturally to general logic programs.     

税控收款机中间件设计

税控收款机中间件的设计采用分层结构的思想,以异构的硬件平台为基础,可方便的进行应用程序的移植与调试工作。同时对分层模块采用构件化的设计思想,给出了模块部分构件的设计模型,满足了可移植性和可靠性要求,增强了系统的通用性。     

Using Neural Networks to Modularize Software

This article describes our experience with designing and using a module architecture assistant, an intelligent tool to help human software architects improve the modularity of large programs. The tool models modularization as nearest-neighbor clustering and classification, and uses the model to make recommendations for improving modularity by rearranging module membership. The tool learns similarity judgments that match those of the human architect by performing back propagation on a specialized neural network. The tool's classifier outperformed other classifiers, both in learning and generalization, on a modest but realistic data set. The architecture assistant significantly improved its performance during a field trial on a larger data set, through a combination of learning and knowledge acquisition.     

基于神经网络和规则的专家系统的应用研究

本文对专家系统在材料加工领域的应用特点及现状进行了分析与研究，采用基于人工神经网络和规则的知识表示和获取方法，实现了一个混合型的专家系统；并结合实例，讨论了神经网络与专家系统的集成，以及系统的程序框架与功能设计、各模块的主要实现思路；最后，通过实验数据验证，系统的泛化结果误差小于6％。     

基于深度强化学习与旋量法的机械臂路径规划EI北大核心CSCD

深度强化学习在机械臂路径规划的应用中仍面临样本需求量大和获取成本高的问题.针对这些问题,本文基于数据增强的思路,提出了深度强化学习与旋量法的融合算法.本算法通过旋量法将与环境交互所得的自然轨迹进行有效复制,使深度强化学习样本利用率和算法训练效率得到提高;复制轨迹的同时对被控物体、障碍物等环境元素进行同步复制,以此提高机械臂在非结构环境中的泛化性能.最后,在具备物理模拟引擎的Mujoco仿真平台中,通过Fetch机械臂和UR5机械臂在非结构化环境下进行实验对比分析,结果表明了本文算法对于提升深度强化学习样本利用率和机械臂模型泛化性能的可行性及有效性.     

Generalizing predicates with string arguments

The least general generalization (LGG) of strings may cause an over-generalization in the generalization process of the clauses of predicates with string arguments. We propose a specific generalization (SG) for strings to reduce over-generalization. SGs of strings are used in the generalization of a set of strings representing the arguments of a set of positive examples of a predicate with string arguments. In order to create a SG of two strings, first, a unique match sequence between these strings is found. A unique match sequence of two strings consists of similarities and differences to represent similar parts and differing parts between those strings. The differences in the unique match sequence are replaced to create a SG of those strings. In the generalization process, a coverage algorithm based on SGs of strings or learning heuristics based on match sequences are used. Ilyas Cicekli received a Ph.D. in computer science from Syracuse University in 1991. He is currently a professor of the Department of Computer Engineering at Bilkent University. From 2001 till 2003, he was a visiting faculty at University of Central Florida. His current research interests include example-based machine translation, machine learning, natural language processing, and inductive logic programming. Nihan Kesim Cicekli is an Associate Professor of the Department of Computer Engineering at the Middle East Technical University (METU). She graduated in computer engineering at the Middle East Technical University in 1986. She received the MS degree in computer engineering at Bilkent University in 1988; and the PhD degree in computer science at Imperial College in 1993. She was a visiting faculty at University of Central Florida from 2001 till 2003. Her current research interests include multimedia databases, semantic web, web services, data mining, and machine learning.     

严格凸二次规划的拟单纯解法

本提出一个不用Kuho-Tucker条件而直接搜索严格凸二次规划最优目标点的鲁棒方法。在搜索过程中,目标点沿约束多面体边界上的一条折线移动。这种移动目标点的思想可以被认为是线性规划单纯形法的自然推广,在单纯形法中,目标点从一个顶点移到另一个顶点。     

The Whitney reduction network: a method for computing autoassociative graphs.

This article introduces a new architecture and associated algorithms ideal for implementing the dimensionality reduction of an m-dimensional manifold initially residing in an n-dimensional Euclidean space where n > m. Motivated by Whitney's embedding theorem, the network is capable of training the identity mapping employing the idea of the graph of a function. In theory, a reduction to a dimension d that retains the differential structure of the original data may be achieved for some d < or = 2m + 1. To implement this network, we propose the idea of a good-projection, which enhances the generalization capabilities of the network, and an adaptive secant basis algorithm to achieve it. The effect of noise on this procedure is also considered. The approach is illustrated with several examples.     

基于主方向重建的SURF多角度识别匹配算法优化

针对物体多角度识别过程中存在着因偏转和俯仰角偏差而造成的匹配精度低等问题,本文提出了具有旋转不变性的SURF匹配优化思想.本思想采用聚类算法将提取的关键点进行分类,在类中通过距离高斯加权来得到关键点水平和垂直方向的Haar小波值,进而更精准地确定特征点主方向;针对匹配过程中出现的误匹配对,利用误匹配粗减思想进行剔除;之后,为进一步提高匹配机率,采用物体环视全景图作为后台基准图像.实验结果表明,本思想对物体多角度图像的识别机率和识别正确率明显提高,且匹配耗时也有所减低,并具有一定的实用性和推广性.     

The stress recovery procedure for the finite element method

The idea of the proposed stress recovery procedure has been explained, peculiarities of its realization have been demonstrated on the example of the plane problem with small deformations, and generalization of this procedure to problems with finite deformations has been carried out. The proposed procedure allows us to construct the stress field for the problems with small and finite deformations without numerical differentiation of the displacement field obtained by the finite element method. Firstly, in accordance with this procedure the distributed forces are defined on three internal surfaces (in general case) within the body. This problem is reduced to solving the systems of linear algebraic equations of low-dimensions with symmetrical and positive definite band matrices. It is one of the advantages of the proposed procedure in contrast with other methods of the stress field construction. Then, using the Cauchy relation, the components of the stress tensor or displacement vector increment derivative are computed for the nodes of the finite element grid.