经典的BPN人工神经网络例子源码 ，很经典的

遗传算法 多目标的优化 是用GAOTV包做的-GA multi-objective optimization is done with the package GAOTV

基于点轨迹的手势识别.鼠标右键点击开始记录鼠标轨迹,基于记录的轨迹,利用神经网络算法进行识别.-Trajectory based on the point of gesture recognition. By right-clicking the mouse to start recording the track, based on track record, the use of neural network algorithm to identify.

用AMZI做的只能西湖地图，初学者做，人工智能-AMZI do with the only West Lake maps, beginners do, and artificial intelligence

BP分类器，用与识别不同模式。-BP classifier, and used to identify different models.

一个遗传算法C++类,值得收藏！-a genetic algorithm C-worthy collection!

10。《用于最优化的计算智能》，Nirwan Ansali，Edwin Hou着，李军，边肇棋译 清华大学出版社 1999年第一版 本书从讨论组合优化中的基本问题――NP问题入手，系统地讲述了近年来所发展起来的智能最优化的各种技术和方法，其中包括启发式搜索、Hopfield神经网络、模拟退火和随机机、均场退火以及遗传算法等；并在此基础上，通过一些典型的应用问题，如旅行商问题、模式识别中的点模式匹配问题、通信和任务调度等问题进一步阐明以上一些基本方法怎样用来解决这些原来具有NP性质的困难问题。本书是作者在美国新泽西州理工学院多年讲授有关课程的基础上写成的。全书深入浅出，理论联系实际。为帮助学生掌握基本概念，提高学习能动性，各章编写了习题。本书可作为通信、计算机、控制各专业的高年级学生和研究生学习有关课程的教材。它对于广大科研工作者也是一本很有实际价值的参考书。 -10. "Optimal for Computational Intelligence," Nirwan Ansali, with Edwin Hou, Li Jun, Pin Zhaoxing chess translation Tsinghua University Press in 1999 the first book version of combinatorial optimization from the discussion of basic questions-- NP problem start, the system described in recent years to develop the intelligent optimization of the technology and methods, These include heuristic search, Hopfield networks, simulated annealing and random machine, mean field annealing and genetic algorithms; and on this basis and through some typical applications, such as the traveling salesman probl

MILK 提供了一个实现和比较multi-instance学习算法的环境，基于weka机器学习系统（本站可以下载）-MILK provides a comparison and achieve multi-instance learning algorithm, based on machine learning system weka (site can be downloaded)

很好的程序，MATLAB-good procedures, MATLAB

可以自动生成qbf问题实例,但需要给定一些参数.-can produce QBF instance

This demo nstrates the use of the reversible jump MCMC simulated annealing for neural networks. This algorithm enables us to maximise the joint posterior distribution of the network parameters and the number of basis function. It performs a global search in the joint space of the parameters and number of parameters, thereby surmounting the problem of local minima. It allows the user to choose among various model selection criteria, including AIC, BIC and MDL