基于Fisher准则线性分类器设计，理解Fisher准则方法确定最佳线性分界面方法的原理，以及Lagrande乘子求解的原理。...

用vc写的，同时有用bp算法和用rbf神经网络进行训练和识别的程序，可以看到两种不同方法得到的结果-vc used to write, while useful bp algorithm and the use of rbf neural network training and identification procedures, we can see the two different methods to obtain the result

HIGHLIGHT TRUE #define NOHIGHLIGHT FALSE #define UPDATE TRUE #define NOUPDATE FALSE #define FORMAT TRUE #define NOFORMAT FALSE #define LEFT 0-HIGHLIGHT# define NOHIGHLIGHT TRUE FALSE UPDATE# define TRUE## define FALSE de NOUPDATE fine FORMAT# define TRUE FALSE# defin NOFORMAT e LEFT 0

收集的关于遗传算法的模糊搜索的ppt资料，有兴趣的可以研究一下-Collected on the genetic algorithm ppt fuzzy search information, interested can look at

神经网络中的竞争网络聚类-neural network competition in the network clustering

可以用C++语言开发各种神经网络：BP，RBF，HOP~…………，使用前请看看说明文档，然后建立一个自己的项目文件，只要能明白作者的思路就能很方便地进行各种神经网络的设计，本人现在就在一个系统中使用它，目前这个开发包的版本已进入0.7了，但功能差不多，本人认为0.5这个版本用着也很方便，所以把他发来，大家共享。-C language can be used to develop a variety of neural networks : BP, RBF, HOP ~ ... ... please look at the use of pre-documented, and then the establishment of a project document, you will be able to understand the author"s ideas will be very convenient for the various neural network design, I in a system in which to use it, the current version of the development kit has entered 0.7, but the function almost, I think that this version of 0.5 is also very convenient, so he made to share.

人工神经网络BP算法 1、动态改变学习速率 2、加入动量项 3、运用了Matcom4.5的矩阵运算库（可免费下载,头文件matlib.h)， 方便矩阵运算,当然，也可自己写矩阵类 4、可暂停运算 5、可将网络以文件的形式保存、恢复-Artificial neural network BP algorithm 1, the dynamic change learning rate 2, adding momentum of 3, using the matrix calculation Matcom4.5 library (can be downloaded free of charge, the first document matlib.h), facilitate the matrix calculation, of course, can also write their own matrix Class 4, may be suspended by the operator 5, may be the form of network to the preservation, restoration

最邻近的RBF算法,MATLAB实现,较为有价值的资料.-The nearest RBF algorithm, MATLAB realize, the more valuable information.

十折交叉验证方法的matlab code 再模式识别中是一个非常重要的试验方法-a very important technique crossvalidate in pattern recognazition

程序包含的设置包括：列数、样本总个数、建模样本数、预报因子数、预报对象数、学习因子、 动量因子、训练次数、总体误差、隐节点数。-procedures contained in the set include : number, the total sample number, the number of samples modeling, forecasting several factors, forecasting several targets, learning factor, momentum factor, the number of training, the overall error of hidden nodes.

pso 的一个演示源码，欢迎初学者下载，共同进步-pso source of a presentation, please download beginners, and common progress! ! ! ! ! !