用免疫算法来实现TSP问题的求解，程序全，可以运行。

加了动量项和域值，比较好用的bp网络算法-added value items and Victoria, better quality bp Network

FCM算法是一种基于划分的聚类算法，它的思想就是使得被划分到同一簇的对象之间相似度最大，而不同簇之间的相似度最小。模糊C均值算法是普通C均值算法的改进，普通C均值算法对于数据的划分是硬性的，而FCM则是一种柔性的模糊划分。在介绍FCM具体算法之前我们先介绍一些模糊集合的基本知识。-FCM algorithm is a clustering algorithm based on the division of its thinking is that it is making is divided into clusters with the greatest similarity between the object, and different similarity between the smallest cluster. Fuzzy C-means algorithm is an ordinary C-means algorithm, the general C-means algorithm for data delineation is rigid, while the FCM is a soft fuzzy partition. FCM in the introduction prior to the specific algorithm we first introduce some basic knowledge of fuzzy sets.

一个用C编写的SOM（自组织特征映射）神经网络源代码。-a C prepared by the SOM (self-organizing feature map) neural network source code.

模拟退火生成树，一种比较好分类方法。程序简单，易懂。-simulated annealing Spanning Tree, a better classification. Simple and straightforward.

手写汉字识别 应用SVM和神经网络进行识别,可自行训练-Handwritten Chinese Character Recognition Application of SVM and neural networks to identify their own training

这是一个用matlab编制的DE算法的源程序，希望大家喜欢！-This is a preparation using the Matlab DE algorithm source, hope you like them!

一个大家都在寻找的em算法，matlab实现-one we are looking for the em algorithm, achieving Matlab

粒子群算法程序集,应用于粒子优化处理!最新的算法.-PSO algorithm set, optimized for particle! The latest algorithm.

新型模拟退火算法解决TSP优化问题。自能退火。可用于大多数情况下的优化问题。-New simulated annealing algorithm to solve TSP optimization problem. Zineng annealing. Can be used in most cases the optimization problem.

网络为３层结构，输入层为６个神经元，隐含层为４个神经元，输出层为１个神经元，当输入层为中心对称样本 1，0，0，0，0，1等时，网络输出为1，否则输出为0。-network of three-layer structure, input layer to six neurons to the hidden layer 4 neurons, the output layer to a neuron, when the input layer to the center symmetry samples such as 1,0,0,0,0,1, the output of a network, the output is 0.