Boole函数的线性可分性(Ⅰ)——n-维超立方体的基本理论

Boole函数的线性可分性是前向人工神经网络理论中的一个比较困难的问题之一。目前仅对变量数n≤7的某些问题给予讨论。当n≥8时,尚无判别Boole函数线性可分的一般准则,更无线性可分Boole函数的计数公式。基于此,本文详细地研究了与Boole函数线性可分性有关的n-维超立方体的基本理论,包括n-维超立方体的基本性质、超立方体中的平行线、子超立方体的计数等,并给出了构造n-维超立方体图的一种新方法。     

非线性干涉滤光片开关特性及逻辑功能

应用干涉滤光片作为一种光学双稳器件,演示了光学逻辑开关功能。     

STRESS INTENSITY FACTORS AND WEIGHT FUNCTIONS FOR SEMI-ELLIPTICAL SURFACE CRACKS IN FINITE-THICKNESS PLATES UNDER TWO-DIMENSIONAL STRESS DISTRIBUTION

Abstract— A Fourier series approach is proposed to calculate stress intensity factors using weight functions for semi-elliptical surface cracks in flat plates subjected to two-dimensional stress distributions. The weight functions were derived from reference stress intensity factors obtained by three-dimensional finite element analyses. The close form weight functions derived are suitable for the calculation of stress intensity factors for semi-elliptical surface cracks in flat plates under two-dimensional stress distributions with the crack aspect ratio in the range of 0.1 ≤ a/c ≤ 1 and relative depth in the range of 0 ≤ a/t ≤ 0.8. Solutions were verified using several two-dimensional non-linear stress distributions; the maximum difference being 6%.     

一类广义几何序列的相关函数

计算序列的周期相关函数是一个很困难但又十分重要的问题。本文首次给出了线性相关广义几何序列的相关函数，从而部分地解决了Ｋｌａｐｐｅｒ提出的相关函数计算问题。     

提高前馈神经网络推广能力的若干实际方法

提高前馈神经网络的推广能力是深受关注的问题，本文根据我们最近提出了一个网络有效推广的准则，从提高网络特征提取能力，分类能力和修改神经元激活函数等几方面给出了若干实际方案，我们在任意手写数字识别问题上的实验结果证实了这些方法的有效性。     

一种基于三次样条函数求离子浓度的自动算法

本文提出了一种用三次样条函数模拟双次标准加入法测量方程，直接求解离子浓度的自动算法。比较了三咱不同边界条件下用要池数计算离子浓度的结果。造出节点区间两极端点的二阶导数为零时的三次样条函数为最佳模拟函数。并讨论了该方法在实际分析中误差的来源及消除办法。经对一系列文献数据的验算对比，表明本法完全可代替传统的迭代法和查图法，且能方便地设置在智能化的电位分析系统中。     

中国古典园林三维造型研究

论述了采用层次结构化及参数化三维造型方法，建立一个以造型函数库为核心，从而构造各类、各级园林景观构件表面模型的方法和过程。对于某些非建筑类的园林配景构件，采用了Ｆｒａｃｔａｌ方法进行造型。     

BP算法的改进及用模拟电路实现的神经网络分类器

基于用模拟电路实现神经网络分类器的目的，对多层静态前馈神经网络的ＢＰ算法做了改进，采用线性限幅函数代替Ｓｉｇｍｏｉｄ函数作为神经元的激活函数，给出了改进的ＢＰ算法。对该算法性能的实验研究表明：这种改进算法不但方便了用线性模拟集成运算放大电路实现神经网络，而且具有学习速度快，映射能力强等优点。根据本文算法设计的神经网络分类器，无论是计算机仿真，还是模拟电路实现，都得到了比较高的识别率。     

Qualitative representation of spatial knowledge in two-dimensional space

Various relation-based systems, concerned with the qualitative representation and processing of spatial knowledge, have been developed in numerous application domains. In this article, we identify the common concepts underlying qualitative spatial knowledge representation, we compare the representational properties of the different systems, and we outline the computational tasks involved in relation-based spatial information processing. We also describesymbolic spatial indexes, relation-based structures that combine several ideas in spatial knowledge representation. A symbolic spatial index is an array that preserves only a set of spatial relations among distinct objects in an image, called the modeling space; the index array discards information, such as shape and size of objects, and irrelevant spatial relations. The construction of a symbolic spatial index from an input image can be thought of as a transformation that keeps only a set of representative points needed to define the relations of the modeling space. By keeping the relative arrangements of the representative points in symbolic spatial indexes and discarding all other points, we maintain enough information to answer queries regarding the spatial relations of the modeling space without the need to access the initial image or an object database. Symbolic spatial indexes can be used to solve problems involving route planning, composition of spatial relations, and update operations.     

冷轧形变量对钛板材再结晶织构形成的影响

采用三维晶体学取向分布函数（ＣＯＤＦ）分析法研究了工业纯钛板材不同冷轧形变量对织构形成的影响。结果表明，冷轧形变量为５０－７０％时，再结晶退火后形成了（２１１８）（０１１０）和（１０１８）（１２１０）的部分纤维织构，而在３０％较低或８６％较高的形变量冷轧时，形成典型的轧制织构（２１１５）（０１１０）和再结晶织构（１０１３）（１２１０）型式。