小波十讲(中文版),这是个很好的讲义，希望对你有帮助

将遗传算法(GA)与传统SVM算法结合,构造出一种参数最优的进化SVM(GA2SVM),SVM 模型采用径向基函数(RBF)作为核函数，利用格雷码编码方式对SVM算法的模型参数进行遗传编码和优化搜索，将搜索到的优化结果作为SVM 的最终模型参数。-Genetic algorithm (GA) combined with the traditional SVM algorithm, a kind of tectonic evolution of the optimal parameters of SVM (GA2SVM), SVM model using Radial Basis Function (RBF) as kernel function, the use of Gray code encoding algorithm of the SVM model parameters of genetic coding and optimization of search, will search for the optimal results as the final SVM model parameters.

聚类分析简介，是个课件，希望对大家有帮助。-Introduction Cluster analysis is a courseware, we want to help.

转载：对神经网络中使用最广泛的一种：BP神经网络采用vbmatlab来实现，把训练数据拷入，load的*.m文件中, 文件中部load的*.m为测试数据 save 存盘的文件为测试数据的bp预测值, 该程序可以扩充n个输入,n个输出,很容易-reproduced : the neural network the most widely used one : BP vbmatlab using neural networks to achieve, it is copyed into the training data. m*. load the document, Central to the paper load*. m to save Inventory test data for the paper test data bp predictive value, The procedure can be expanded to import n, n output, it is easy

有指导的马尔可夫随机场（MRF）的图像分割代码，是有指导的方式（即用鼠标框出分类样本区域）。采用OpenCV编写。-Has guided Markov Random Field (MRF) image segmentation code, is guiding the way (that is, a classification of the box with the mouse sample region). Prepared using OpenCV.

pre-fixSpan算法，该算法是C++语言实现的，主要用模板实现prefixspan的投影数据库架构及模式生长功能

各种数值算法，包括：二叉树、贪心算法、搜索算法、遗传算法、模拟退火算法、分治策略等等。-A variety of numerical algorithms, including: binary tree, greedy algorithm, search algorithm, genetic algorithm, simulated annealing algorithm, sub-rule tactics and so on.

宽度优先搜索法见cpp1.cpp文件，在vc6.0环境运行实现-width priority search see cpp1.cpp documents in the operation to achieve environmental vc6.0

Neural Networks ，8种神经网络，BP，RBF，CPN等通过VC++来实现了！-Neural Networks, 8 Neuro network, BP, RBF, CPN, such as through VC++ To achieve!

开发环境：Visual C++ .net2003 功能介绍：神经网络算法实验；分Console版本和MFC版本；主要用来求解TSP问题。-Development Environment: Visual C++. Net2003 function introduction: neural network algorithm experiments sub-Console version and MFC version mainly used to solve the TSP problem.

基于canny的灰色预测和模式识别,标定的一种做法是：在一块平板上画若干个点， 同时用这两部相机照相，分别得到这些点在它们像平面上的像点，利用这两组像点的几何关系就可以得到这两部相机的相对位置。然而，无论在物平面或像平面上我们都无法直接得到没有几何尺寸的“点”。实际的做法是在物平面上画若干个圆（称为靶标），它们的圆心就是几何的点了。而它们的像一般会变形，如图1所示，所以必须从靶标上的这些圆的像中把圆心的像精确地找到，标定就可实现。-Based on the gray canny prediction and pattern recognition, calibration approach is to: a plate painted in a number of points, at the same time with these two cameras camera, respectively, as these points in their plane as points, the use of these two groups geometric relationship between the image point can be that the relative positions of two cameras. However, in terms of objects such as plane or plane, we can not directly be no geometry point. Actual practice is complex plane painted in a number of round (known as targets), their geometric center of a circle is the point. And they generally like deformation, as shown in Figure 1, it must target these round, like in the center of a circle of like to find precise, calibration can achieve.