简单一元函数优化实例，利用遗传算法计算下面函数的最大值...

BP人工神经网络算法的实现，用java代码编写，案例是港口吞吐量预测。

已知北京、上海、广州、昆明和西安五城市航线里程如图。分别实现： 1）找到北京到昆明的最短路径。 2）找到北京到昆明，必须途径上海的路径。 3）找到北京到昆明，必须途径上海，但不能去广州的路径。 -known Beijing, Shanghai, Guangzhou, Kunming and Xi"an City route five mileage figure. Were achieved : 1) to Kunming to Beijing to find the shortest path. 2) find Beijing to Kunming, Shanghai must channel"s path. 3) to find Beijing to Kunming, Shanghai must channels, but can not go to Guangzhou"s path.

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.

自己用swarm开发的一个车辆跟驰的模型，希望能跟广大爱好者共同探讨。-own use development of a swarm of vehicles- following model, the majority of fans are able to explore together.

模拟3G环境，测试可伸缩视频码流，适合JSVM开发者-Analog 3G environment, testing, scalable video stream, suitable for JSVM developers

利用人工智能原理中BP神经网络算法，建立的彩票预测程序，当然不可能都预测中，但是要学习神经网络的人值得一看-BP neural network algorithm, the establishment of the lottery forecasting process, of course, not all forecasts, but neural networks to study the eye-catcher

用模拟退火算法解决TSP问题，在C运行环境中-TSP with ant colony algorithm to solve the problem in the C runtime environment

麻省理工大学遗传算法 -Massachusetts Institute of Technology Massachusetts Institute of Technology genetic algorithm genetic algorithm

一个外国人写的字符识别训练源码，VC++源码，有源码、说明及演示可执行程序，对学习和研究模式识别很有帮助。-written by a foreigner Character Recognition training source, VC source, a source that, and the demonstration of the executable, on learning and pattern recognition research helpful.

java编写的贝叶斯网络分类器（貌似没有模型构建和参数学习过程）-java prepared by the Bayesian network classifier (seemingly no model of the learning process and parameters)