查询词典 iterated kernel

Then we introduced transition probability kernel for the hidden state process and the confederated process. In the deep research, we found that some similar parameters of state transition probability, observation symbol probability and initial state probability were involved in the transition probability kernel of the confederated process. So we can complete the training of traditional HMM parameters by training the transition probability kernel of the confederated process. To our surprised, we got the consistency of transition probability kernel of the confederated process. Meanwhile, we proved the rationality and reliability of the parameters estimation equations under the classical B-W algorithm.

然后对联合过程的转移概率核展开研究，我们根据过程的取值空间的不同，引入了隐状态空间和联合过程空间上的转移概率核，研究中发现在联合空间上的转移概率核包含了在一般的隐马氏模型的参数估计中的所有类似的三组参数(转移概率，观测概率和初始概率)，因此对传统的隐马氏模型的参数训练我们可以通过联合过程的转移概率核的训练来完成，更令我们惊奇的是联合过程的转移概率核还具有一致性；同时对于Baum提出的经典的B-W算法给出的关于模型的参数重估计公式，证明了它的合理性和可靠性，即模型经过重估计后的参数能够满足给定的单观测序列在模型下发生的概率是单调递增的。

Researches on kernel clustering algorithms. After combining K-means clustering algorithm and the theory of kernel-based learning algorithms, we propose a fast kernel K-means clustering method which is based on CPD kernel. The experiment results indicate that the clustering effect of the algorithm is better than that of K-means algorithm, the clustering speed of the algorithm is also fast than that of K-means algorithm.

核聚类算法的研究：探讨了K-均值聚类算法，通过将核学习理论与K-均值聚类算法结合，提出了一种基于CPD核函数的快速核K-均值聚类算法，并将该算法与基于Mercer核的核聚类算法进行了比较，实验结果显示，我们的方法不仅比K-均值聚类算法的聚类效果好，而且聚类速度快。

In this paper, we study the finite iterated order of growth and the iterated convergence exponent of the zero sequence of nonzero meromorphic solutions of second order homogeneous linear differential equation , and obtain some precision evaluation.

摘要研究了二阶齐次线性微分方程非零亚纯解的迭代级与零点迭代收敛指数，得到了它们的精确估计。

We also present iterated function systems 、local iterated function systems、Barnsley's collage theorem and Markov's theorem.

我们也介绍了迭代函数系统、局部迭代函数系统、Barnsley的拼贴定理和Markov定理。

This paper will mainly discuss the Law of Iterated Logarithm for some kind weighted partial sum. It is an extension of "the Law of Iterated Logarithm of Kolmogorov".

本文主要讨论独立随机变量某种加权和重对数律，它是"Kolmogorov重对数律"的推广。

By the reconstruction of the coefficients of the affined transformation of iterated function systems with probability vector, this makes the dynamic iterated question a static one, and makes it a typical one rank linear recurrence question.

基于代数算法的思想，对Hilbert曲线向三角域作了推广。

By using the concept of iterated order,we investigate the Borel direction of the derived functions of meromorphic functions with iterated order.

利用亚纯函数的迭代级的概念，研究了迭代级亚纯函数导函数的Borel方向。

By comparing the activity of theα-amylase and the soluble acid invertase in the kernel and the pedicel, the trend of theα-amylase activity in the kernel and the pedicel showed a peak, theα-amylase activity was high in the early stage, it could promoted amylolysis, supply the nutrition for the kernel development; theα-amylase activity was low in the rapid filling stage, it was in favorable to the starch accumulation.

通过比较籽粒和小穗柄中α-淀粉酶和可溶性酸性蔗糖转化酶的活性表明，籽粒和小穗柄中α-淀粉酶活性均呈单峰变化趋势，籽粒发育早期α-淀粉酶活性较高，可以促使淀粉转化，为籽粒的早期的发育提供营养物质；籽粒发育中期为快速灌浆期，淀粉酶活性较低，利于淀粉的积累。

Algorithm application of neural networks.Ⅲ Implementation of neuro-computers. The main contribution of the dissertation can be summarized as follows: 1 Hopf bifurcation of three kind of neural networks are discussed in detail, including type of discrete time delay, type of time delay with weak kernel and strong kernel as well as the proof of existence of bifurcation. Other problems such as asymptotic stability of bifurcation periodic solution, algorithm of determining the bifurcation direction, asymptotic stability and style of periodic solution are also studied. The average time delay is chosen as the bifurcation parameter, phenomena pertinent to system states of the continuous time delay network with strong kernel evolving from stable to oscillating, then back to stable again are observed.

论文的主要创新之处可以归纳如下： 1）针对目前国内外对神经网络的分岔研究较少的情况，论文中详细讨论了带离散时延神经网络、带弱核的连续时延神经网络、带连续分布时延且具有强核的神经网络的Hopf分岔现象，从理论上证明了Hopf分岔的存在性，并研究了分岔周期解的渐近稳定性，得到了确定周期解的渐近稳定性、分岔方向、周期解的渐近形式的算法；用平均时延作为分岔参数，发现带强核的连续时延神经网络中存在着系统的状态由稳定变化到振荡现象，当继续增加平均时延参数时，又从振荡变为稳定这一特殊的动力学现象。

Dorea advanced kernel estimation p of p ,which is a general density with respect to a σ-finite measure v on.ξ is a σ-field of subsets of ER. Some qualities have been gotten. And it has been proved that those results consist of theories of classical kernel estimation for continual density and further extended theories of disperse kernel estimation.

Y Dorea在2001年提出了关于上的σ-有限测度v的一般密度函数P的核估计几，其中ER，ξ是E的一个σ-域，得到了一些结果，并且验证了所得结论包含经典的连续密度核估计的结论，还进一步延伸了离散分布核估计的结论。

Nowadays, most of research are to build a transmutative Petri Nets through adding controlling place sets, controlling arc sets and controlling policy to the basic Petri Nets, while the Controlled Petri Nets could be used to argue many controlling theory problems conveniently and to induce many logically and physically supervisory and solve the Event Feedback Controlling Problems and State Feedback Controlling Problem in DEDS supervisory theory.

目前大多数的研究表现为在变形后的受控Petri网基础上，利用各种方法求得各种逻辑型、结构型控制器，解决DEDS监控理论中的事件反馈控制问题与状态反馈控制问题。

On one hand, there are discussions with the works council and union about extension of short time working up to the end of September.

一方面，有讨论，工程理事会和联盟关于延长工作时间短至9月底。