正态分布 normal VBA 代码

通常MCIL假设一个包中的实例是独立分布的，不考虑实例间的内部依赖关系，但是这样，如果属于正的实例是噪声，则会有误差，所以考虑上下文关系（邻居点），增强MCIL的鲁棒性。将聚类的概念引入到多示例学习中 完成图像的分割和聚类。

应用背景利用VHDL实现FFT变换，FFT在FPGA中用处比较多，可以帮助大家很好认识FFT变换之后频谱。。。关键技术VHDL实现FFT变换, 旋转因子是FFT实现的难点和重点。。。。。。。。。。。。。。。。。。。

数据挖掘 聚类算法 k-means的实现，改进了一些初始中心选取的方法。聚类算法是最大化类间差异，而最小化类内部差异的算法，k-means比较经典，但是缺点是需要指定k值，并且聚类结果与初始中心有很大的关系，通过改善聚类初始中心选取的方法，能够得到更加稳定的聚类结果

calculator,used for computing

学习CFD的基础教程，含有各种差分格式和高精度本质无振荡算法源程序。-learning CFD based directory containing a variety of formats and high-precision differential nature without oscillation algorithm source.

高斯-赛德尔迭代求解线性方程组.很实用的数学计算软件-Gauss- Seidel method for solving linear equations. Very useful mathematical calculation software

This matrix C++ template class library is for performing common matrix operations in your C++ program like any other built-in data types. To install the package, just copy MATRIX.H file into the INCLUDE directory of your compiler and include this header file in your program source file

滤波器的设计一直是信号 iiii 重要问题处理。kCdUSe intinite 冲激响应 (IIR) 滤波器有liequency 选择和高精度的良好特性与较低的订单，它 atlracts 很多研究者的关注，是一般应用于许多领域。通讯技术、 雷达信号处理、 语音和图像信号处理。数字过滤、-IDTV。等。因为那里是没有分析方法显然当 IIR设计了数字分蘖与任何频率响应，一般采用优化方法。在本文中，NQGA 用于优化设计 01" IIR 数字分蘖频率域直接。

数据挖掘是信息产业界近年来非常热门的研究方向，聚类分析是数据挖掘中的核心技术。本文对数据挖掘领域的聚类分析方法及代表算法进行分析，并从多个方面对这些算法性能进行比较，同时还对聚类分析在数据挖掘中的几个应用进行了阐述。-Data Mining is the IT industry is very popular in recent years the direction of the research, cluster analysis is data mining in the core technology. In this paper, the field of data mining methods and the representative of cluster analysis algorithm analysis, and from several aspects of these algorithms to compare the performance, but also on the cluster analysis of data mining in several applications are described.

ASDAASDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDAASDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDdddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd