bp神经网络变形预测源程序(有待改进),很短的一段代码，所有直接写在TXT文件中。...

程序包含的设置包括：列数、样本总个数、建模样本数、预报因子数、预报对象数、学习因子、 动量因子、训练次数、总体误差、隐节点数。-procedures contained in the set include : number, the total sample number, the number of samples modeling, forecasting several factors, forecasting several targets, learning factor, momentum factor, the number of training, the overall error of hidden nodes.

双向广度优先搜索算法法见8SM2.cpp文件，vc6.0环境运行实现-two-way breadth- first search algorithm see 8SM2.cpp France, achieving operating environment vc6.0

Demonstration and test of the kernel-ica package

文件中包含某老师关于智能优化计算课程中的遗传算法部分的讲义，其中包含详细的例子及源代码。-File contains a calculation of the teachers on the intelligent optimization of the genetic algorithm curriculum part of the lecture, which includes detailed examples and source code.

Collection of 30+ AI Neural Network java applets with documentation.

一个Ｃ编写的足球机器人比赛程序，算法很好-C prepared by a robot soccer competition procedures, a good algorithm

利用动量梯度下降算法训练BP网络，得到误差显示图，并最终进行预测-Gradient descent algorithm using momentum BP network training, the error display map, and, ultimately, to predict

完整的3D 模型检索程序，使用C语言编写，可以使学习者从底层研究三维模型的检索框架，同时提供的C语言程序包也可以设计新的三维模型检索算法。-Complete 3D model retrieval, the use of C language, so that students can study three-dimensional model from the bottom of the search framework to provide the C language package can also be three-dimensional model of the design of the new search algorithm.

神经网络程序设计，遗传算法-neural network programming, genetic algorithm

由于K－均值聚类算法局部最优的特点，而模拟退火算法理论上具有全局最优的特点。因此，用模拟退火算法对聚类进行了改进。20组聚类仿真表明，平均每次对K结果值改进8次左右，效果显著。下一步工作：实际上在高温区随机生成邻域是个组合爆炸问题（见本人上载软件‘k－均值聚类算法’所述），高温跳出局部解的概率几乎为0，因此正考虑采用凸包约束进行模拟聚类，相关工作正在进行。很快将奉献给各位朋友。-as K-means clustering algorithm for optimal local characteristics, and simulated annealing algorithm theory with the characteristics of the global optimum. Thus, simulated annealing algorithm for clustering improvements. Cluster Group of 20 simulations show that the average value of K results improved about eight times, the results are obvious. The next step : In fact, in high temperature generated random neighborhood is a combination of explosives (see my software on the "k-means clustering algorithm" mentioned above), high-temperature solution of partial out almost zero probability, it is considering the use of convex hull bound for simulation cluster, the work under way . Soon dedication to the ladies.