经典决策树分类和规则学习模式

二维核密度估计算法.以及最优化计算核宽度。-bivarite kernel estimation

开发环境:Matlab 简要说明:自组织特征映射模型(Self-Organizing feature Map)，认为一个神经网络接受外界输入模式时，将会分为不同的区域，各区域对输入模式具有不同的响应特征，同时这一过程是自动完成的。各神经元的连接权值具有一定的分布。最邻近的神经元互相刺激，而较远的神经元则相互抑制，更远一些的则具有较弱的刺激作用。自组织特征映射法是一种无教师的聚类方法。-development environment : Matlab Brief Description : Self-Organizing Map model (Self-Organizing Map feature), a neural network that external input mode, will be divided into different regions, the regional input to the model with different response characteristics and the process is automatic End %. The neurons connect with the right to a certain value of the distribution. Most neighboring neurons stimulate each other, distant neurons were mutual inhibition, the vision has a weaker stimulus. Self-organizing feature mapping method is a non-teachers clustering method.

这是一篇步态识别和检测的文章：这是在视频流的基础上，区别于以往的静态图像-This is a gait recognition and detection of the article : This is the video stream on the basis of distinguished from the previous static images

Particle Swarm Optimization (PSO) for the TSP

根据人工鱼群算法的基本原理，求解一个函数值的最优解；-According to the basic principles of artificial fish-swarm algorithm, solving a function value of the optimal solution

这是用matlab编的谱聚类程序，该方法能有效的用于数据分类。-This is a matlab procedures for the spectral clustering.The method is effective for data classification.

利用Fisher分类器对数据进行分类，并画出决策面（含测试数据）-Fisher classifier using the data classification, and face painted in decision-making (including test data)

一个运用遗传算法来训练神经网络的程序-use of a genetic algorithm to train the neural network process

以上程序来自水母清华bbs,你可以到学术资源-〉signal->精华区里找， 下面是写这个程序的大虾的补充 发信人: maxxu (小小鸟), 信区: Signal 标 题: Re: 大侠们出手：高斯（白）噪声的c程序实现 发信站: BBS 水木清华站 (Fri Dec 29 16:33:07 2000)-Above procedure from the jellyfish Tsinghua bbs, you can go to academic resources-> signal-> the best area to find, the following is written this procedure to add the sender of the shrimp: maxxu (小小鸟), letter of the district: Signal heading: Re : heroes are hand: Gaussian (white) noise c program letters stand: BBS SMTH Station (Fri Dec 29 16:33:07 2000)

L-M算法。除了动量法(基于梯度下降的训练算法)外，学习率自适应调整策略是BP算法改进的另一种途径，它利用Levenberg-Marquardt优化方法，从而使得学习时间更短。其缺点是，对于复杂的问题，该方法需要很大的存储空间。 -L-M algorithm. In addition to momentum (based on the gradient descent algorithm for training), learning rate adaptive strategy is to improve the algorithm BP Another approach, which uses Levenberg-Marquardt optimization method, which makes learning time is even shorter. Its weakness is that the complex problems that the method requires a lot of storage space.