java bayes的bin文件，enjoy it！

EM algorithm with a Rauch-Tung-Striebel smoother and an M step,内有说明-EM algorithm with a Rauch-Tung-Striebel"s moother and an M step, which is described

在vc控制台中运行，用遗传算法求解最短路径，用邻接矩阵表示路线图。-in vc console operations, Genetic Algorithm for the shortest path, adjacency matrices road map.

一个改进的聚类算法FCMA,可以实现数据的自适应有效聚类,对2维数据测试效果较好- An improvement gathers kind of algorithm FCMA, may auto-adapted realize the data effectively to gather the kind, is better to 2 dimensions according to the test effect

人工神经网络神经网络的程序和训练数据 解压缩后可以运行的-ANN neural network training procedures and decompress data after the run

用的VC6编的可以识别联机数字，联机英文，及联机汉字-the VC6 series of the figures can be identified on-line, on-line English, and Chinese characters on-line

Java神经网络工具箱-Java neural network toolbox

粒子群优化算法(PSO)是一种进化计算技术(evolutionary computation).源于对鸟群捕食的行为研究 PSO同遗传算法类似，是一种基于叠代的优化工具。系统初始化为一组随机解，通过叠代搜寻最优值。但是并没有遗传算法用的交叉(crossover)以及变异(mutation)。而是粒子在解空间追随最优的粒子进行搜索。详细的步骤以后的章节介绍 同遗传算法比较，PSO的优势在于简单容易实现并且没有许多参数需要调整。目前已广泛应用于函数优化，神经网络训练，模糊系统控制以及其他遗传算法的应用领域-Particle Swarm Optimization (PSO) is an evolutionary technology (evolutionary computation). Predatory birds originated from the research PSO with similar genetic algorithm is based on iterative optimization tools. Initialize the system for a group of random solutions, through iterative search for the optimal values. However, there is no genetic algorithm with the cross- (crossover) and the variation (mutation). But particles in the solution space following the optimal particle search. The steps detailed chapter on the future of genetic algorithm, the advantages of PSO is simple and easy to achieve without many parameters need to be adjusted. Now it has been widely used function optimization, neural networks, fuzzy systems control and ot

可用于bp,elman,rbf,grnn四种神经网络的预测命令-Can be used for bp, elman, rbf, grnn four types of neural network prediction order

用人工神经网络实现异或的功能。用反向传播算法（BP）来实现神经网络，正确率可以达到80% -using artificial neural network XOR functions. With back-propagation algorithm (BP) to achieve neural network, can achieve an accuracy rate of 80%

机器人竞赛系列，robocon，，期刊论文-Series of robot competitions, robocon,, Journal Papers