基于SVM局部后验概率融合方法研究

研究了基于支持向量机的后验概率的应用,提出了对样本集进行分解,以产生局部后验概率,根据模式的稳健性对局部后验概率进行凸组合融合的方法.     

市场竞争与国有企业所有权安排

改进了张维迎对地区间竞争与国有企业民营化的分析,给出了经营者的剩余索取份额对竞争性的连续依赖关系:国有企业若要降低成本,就必须参与市场竞争,随着市场竞争的加强,国有企业经营者的剩余索取份额应该逐渐增大,而当市场竞争水平超过某一阈值,国有企业经营者拥有全部剩余索取权是最优的.     

用多焦点全息透镜实现多重谱分数傅里叶变换

提出用多焦点全息透镜实现多重谱分数傅里叶变换.利用全息方法通过一次曝光制作出多焦点的全息透镜,分析了用此全息元件实现这种变换的条件,并在实验上实现了多重谱分数傅里叶变换. 实验结果表明这种变换方法简便可行,可广泛应用于多通道光学信息处理系统及多目标图像识别系统中.     

On the complexity of suboptimal decoding for list and decision feedback schemes

We consider bounded distance list decoding, such that the decoder calculates the list of all codewords within a sphere around the received vector. We analyze the performance and the complexity of this suboptimum list decoding scheme for the binary symmetric channel. The reliability function of the list decoding scheme is equivalent to the sphere-packing bound, where the decoding complexity is asymptotically bounded by 2^nR(1-R). Furthermore, we investigate a decision feedback strategy that is based on bounded distance list decoding. Here, any output with zero or many codewords will call for a repeated transmission. In this case the decoding complexity will be of the order 2^nR(1-C), where C denotes the channel capacity. The reliability function is close to Forney's feedback exponent.     

B—模糊集合代数和广义互信息公式

基于两种概率的区分，推导出了一个广义Shannon熵公式和一个广义互信息公式。后者和模糊性有关，并且柯用于语言和感觉中的信息度量。为了由原子语句为真的条件概率求出合语句为真的条件概率，提出了一个遵循存尔运算的模糊集合代数。所谓的模糊信息被还原为概率信息。新的理论在经典理论－概率论，集合论及Shannon信息论－的基础上容易理解。     

An Informational Approach to the Sinusoidal Law of Photon Polarization

The photon polarization law po ＝ sin2θ is derived from a simple informational consideration by twomethods: The first is via an intuitive principle of mininum Fisher information, the second is via a symmetry andinvariance argument. The results demonstrate that in photon polarization, Nature has a tendency to hide herselfas deepas possible while obeying some regular conditions.     

Supramolecular chemistry

The article discusses molecular recognition and overviews the key concepts -storage and retrieval of chemical information by molecular structures, supramolecular reagents and catalysts, molecular transport, semiochemistry and self assembly. The prospects of controlling supramolecular architecture through engineered molecular recognition and design of ‘programmed systems’ controlled by molecular information are also discussed.     

Pure adaptive search in global optimization

Pure adaptive seach iteratively constructs a sequence of interior points uniformly distributed within the corresponding sequence of nested improving regions of the feasible space. That is, at any iteration, the next point in the sequence is uniformly distributed over the region of feasible space containing all points that are strictly superior in value to the previous points in the sequence. The complexity of this algorithm is measured by the expected number of iterations required to achieve a given accuracy of solution. We show that for global mathematical programs satisfying the Lipschitz condition, its complexity increases at mostlinearly in the dimension of the problem.This work was supported in part by NATO grant 0119/89.     

On the characterisation of paired monotone metrics

Hasegawa and Petz introduced the notion of paired monotone metrics. They also gave a characterisation theorem showing that Wigner-Yanase-Dyson metrics are the only members of the paired family. In this paper we show that the characterisation theorem holds true under hypotheses that are more general than those used in the above quoted references.