人工智能编程示例

遗传优化神经网络结构，C++源代码-Genetic optimization of neural network architecture, C++ Source code

GCP(图着色问题)的模拟退火算法应用源码-GCP (Graph Coloring Problem) application of the simulated annealing algorithm source code

设计的bp神经网络，来判断和预测机器的故障级别。-Bp neural network designed to determine and predict the fault-level machines.

一种运用蚂蚁算法和遗传算法解决旅行商问题的混合优化程序-an ant algorithm and the use of genetic algorithms to solve the traveling salesman problem hybrid optimization procedures

MIT大学的机器学习课程讲稿,很经典的!包括分类,回归,判别式学习,产生式学习,SVM等,基本上包括常用的机器学习算法-MIT University of speech machine learning curriculum, it is classic! Including classification, regression, discriminant study, resulting in learning, SVM, etc., basically including the commonly used machine learning algorithms

BP网络解决异或问题的实例，有初始值和最终结果的显示。本网络结构为三层BP网络，各层神经元个数可变，更改相关#define即可。（注释较详细，主函数中调用的函数和矩阵类都定义在文件function.h中）-BP network to solve XOR problem instance, there are initial values and final results are displayed. The BP network structure for the three-tier network of neurons in the number of floors variable, change the relevant# Define you. (Note more detailed, the main function calls the function and matrices are defined in the document in function.h)

资源分配神经网络解决Mackey-Glass时间序列预测函数逼近问题-Neural network to solve the allocation of resources Mackey-Glass time series prediction function approximation problem

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.

fan_nncC语言神经网络程序包-fan_nncC language neural network package

利用C++语言实现的对运动手势进行识别的代码，请指教！-use C language to the movement of gestures identification code, please advise!