人工智能动物推理系统程序

这是一本进化算法的电子书，很适合人工智能方面的人学习-This is an evolutionary algorithm e-book, it is suitable for artificial intelligence to learn

这是好用的源代码-This is the source code handy

k-means算法(matlab编写),其中包含测试数据集,可以使用.-This is a k-means algorithm(in matlab) contains data set which can be used

匈牙利命名法则，关于在编程中变量的命名的一个很好的参考！-Hungary naming rules，a good reference of naming variables in the programming！

可以用C++语言开发各种神经网络：BP，RBF，HOP~…………，使用前请看看说明文档，然后建立一个自己的项目文件，只要能明白作者的思路就能很方便地进行各种神经网络的设计，本人现在就在一个系统中使用它，目前这个开发包的版本已进入0.7了，但功能差不多，本人认为0.5这个版本用着也很方便，所以把他发来，大家共享。-C language can be used to develop a variety of neural networks : BP, RBF, HOP ~ ... ... please look at the use of pre-documented, and then the establishment of a project document, you will be able to understand the author"s ideas will be very convenient for the various neural network design, I in a system in which to use it, the current version of the development kit has entered 0.7, but the function almost, I think that this version of 0.5 is also very convenient, so he made to share.

人工神经网络bp算法的matlab实现，对bp算法的matlab实现进行了简要的试探-realizing bp arithmetic of neural networks by matlab and exploring it simply.

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.

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.

粒子群算法的vb源程序，可以自定义算法参数，实现对6个非约束性测试函数极小值的全局优化，动态显示粒子的移动。低维下，优化效果很好。直接解压，无须密码。请多指正。-PSO algorithm vb source, the algorithm can define parameters to achieve the six non-binding function tests minimum of global optimization, dynamic display particle movement. Low-dimensional, optimize the results very good. Direct decompression without passwords. Please correct.

自已用C++写的手势辨识,可分出四个不同的手势。-Themselves with C++ Written gesture recognition, can be the separation of four different gestures.