用于求解TSP的蚁群算法，C 语言 已经运行过

BP神经网络的C语言实现 BP神经网络解决异或问题 canny源代码 HMM的C语言实现 isodata K-MEANS 车牌识别系统 矢量量化的C语言实现 -Neural Network C language BP neural network solution differences or problems canny source HMM C language isodata K-MEANS License Plate Recognition System Vector Quantization C Language

用matlab编的，一个典型的BP神经网络的例子，相信对你的学习、工作都能起到一个参考的作用-Using matlab series, a typical example of BP neural network, I believe your study, work can play the role of a reference

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.

基于svm的机器学习文本分类方法，具有很好的借鉴意义-Svm-based machine learning text classification methods, with a good reference

卡内基梅隆大学，采用人工神经网络方法进行人脸训练和识别的c程序源代码，程序中注释比较详细，不多说了。-Carnegie Mellon University, artificial neural network method for training and Face Recognition c source code, procedures Notes in greater detail, not much to say.

这个程序是在windows平台下运行game of life最好的平台。它不仅对细胞空间没有限制、运行速度非常快、界面很友好，而且能够为你提供大量的初始细胞分布图案，你还可以任意组合这些图案达到你象要的构形，然后让这些构形动起来组合出更加神奇的生命游戏的世界。-the procedure is the windows platform running game of life the best platform. It not only on the cell space is no restriction, running very fast, very friendly interface, but you have to provide a lot of initial cell distribution patterns, you can design any combination of these to you as to the configuration, then let these configuration movement combined to make life more wonderful game world.

内附两个源代码，其中一个源代码是识别程序的，另一个是一个矩阵类库的，所以一并附上。 ~..~因为已经保存了训练好的网络权值，所以第一次使用识别程序时，可以直接运行Release目录下的可执行文件，然后对图片目录中的测试图片进行读入、识别。 当然读者也可以自行用训练样本训练网络，不过要特别注意训练样本的选择，否则可能造成识别率很低。训练样本选择的原则是，尽可能的有代表性，在训练时间不至于太长的情况下，训练样本数目尽量多。 -containing 2 source code, which is a source identification procedures, and the other is a matrix class library. So accompanied. ~ ~ .. Has been preserved because of the trained network weights, the first use of the identification procedures, can be run directly Release directory executable file, Then the catalog of tests conducted read into the picture, recognition. Certainly readers can use their own training samples training network, but special attention should be paid to the choice of training samples, Otherwise, it could cause a very low recognition rate. Training sample selection principle is that as far as possible be representative, in the training of the time not too long under the circumstances, the number of training samples as much as possible.

matlab神经网络应用设计-Matlab neural network application design

基于VC的人脸检测系统，可作为一般参考使用，网上搜集所得-VC-based Face Detection system, as a general reference, collected from the Internet

一个人工智能方面的小程序,用OPENGL和VC++做到,希望对大家有所启发-artificial intelligence of a small program, OpenGL and VC done, we hope to inspire