不确定规划 遗传算法 Multilevel Programming算法程序

人工股市（Artificial Stock Market，简称ASM）是模拟股市运作的一个程序。在这个电脑中的虚拟市场中，若干被称为交易者的人工智能程序(Agent)通过观察它们所在的数字世界中股价和股息的不断变换而做出预测，并且根据这些预测做出购买股票与否以及购买股票数量的决策。反过来，所有的交易者的决策又决定了股票的价格，这样，整个的股票交易市场就构成了一个自我封闭的计算系统。同时，这些交易者都具有学习的能力，可以根据以前预测的成功或者失败对自己的决策进行调整，并且通过一种被称为遗传算法的方法产生创新能力。-artificial stock market (Artificial Stock Market, or ASM) is a stock market simulation operation of the procedure. In this computer in the virtual market, a number of traders known as artificial intelligence (Agent) by observing them where the digital world and the stock dividend and the constantly changing projections, and based on these projections made whether or not to purchase stocks and the purchase of shares in decision-making. Conversely, all the decision-making transactions in turn determines the share price, so that the entire stock market would constitute a self-enclosed computer system. Moreover, these transactions are capable of learning, can be predicted based on previous success or failure of their decisions for the

这是一个有关于模式识别中的isodata算法的matlab源码。 大家可以看看。有详细注释-on the isodata pattern recognition algorithm Matlab source. We can look at. Detailed Notes

非线性规划中求解无约束问题中的一个有效方法--模矢法(步长加速法),并用图表示出来步骤.-Nonlinear Programming Solution unconstrained problem of an effective method-- vector mode (step acceleration), and using map out steps.

极小化误差平方和算法聚类源代码，下载后直接运行就可以了-Minimizing the error sum of squares clustering algorithm source code can be run directly after downloading the

改程序实现UB算法，对Web日志文件进行分析，产生相似度矩阵-reform program UB algorithm, the Web log file analysis, the similarity matrix produced

一个神经网络原型代码，针对的例子为《Perceptron Learning》 (Russell & Norvig， 第742页)-A neural network prototype code, for example for

针对现有遗传算法在多维非线性优选方面的不足，本文提出了一种基于小生境进化算法（NEA）的非线性优选模型，探讨了NEA算法的参数选择原则。通过大量仿真和比较，表明算法在复杂非线性优选中具有快速、高效、鲁棒性强的特点，并能在全局范围内有效搜索所有最优解。 -against existing genetic algorithms in three-dimensional nonlinear optimization for the shortage, the paper presents a niche evolutionary algorithm (NEA) nonlinear optimization model, the NEA on the parameters chosen algorithm principle. Through simulation and large, the algorithm shown in a complex nonlinear optimization is fast, efficient, robust features of the strong, and the global scope effective search all the optimal solution.

这是一个我自己编写的JAVA程序，可以运行的。思想是将KMEANS和神经网络结合起来实现模式的分类。-This is a Java program writen by meself which can be run.The chief concept is to combine KMEANS and NN to achieve classification of pattens.

face recognition test 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.