Kohonen network learning process can be described as follows : for each one netw...

模式识别的基础－－相似度量的介绍，对大家可能有帮助-based pattern recognition-- similar to the measure, we might have to help

遗传算法工具箱以及用遗传算法找最优值，主函数是zuiyou.m-Genetic Algorithm Toolbox and using genetic algorithms to find optimal values, the main function is zuiyou.m

我的文件是用VC设计的一个求解人工智能中8数码问题的程序。-my VC document is designed to solve a digital AI 8 issue procedures.

由 Visual C++ 编译过，可以求解任何个数城市的tsp问题，只要输入城市坐标即可。-By Visual C++ Compiled, you can to solve any number of cities tsp, so long as you enter the city coordinates.

仿真1：首先把网络温度参数T固定在100，按工作规则共进行1000次状态更新,把这1000次状态转移中网络中的各个状态出现的次数Si（i＝1，2，…，16）记录下来 按下式计算各个状态出现的实际频率： Pi=Si/∑i=1,NSi=Si/M 同时按照Bo1tzmann分布计算网络各个状态出现概率的理论值： Q（Ei）=（1/Z）exp（-Ei/T） 仿真2：实施降温方案，重新计算 采用快速降温方案：T（t）= T0/（1+t） T从1000降到0.01，按工作规则更新网络状态 当T=0.01时结束降温，再让T保持在0.01进行1000次状态转移，比较两种概率-a simulation : First of all network parameters temperature T fixed at 100 and, according to the rules for a total of 1000 to update the state, this state of the 1000 network transfer of all states for the number of Si (i = 1, 2, ..., 16) all recorded determined by the formula state-of the actual frequency : Pi = Si/i = 1, NSi = Si/M in accordance with Bo1tzmann distributed computing network of states all probability the theoretical value : Q (Ei) = (1/Z) exp (- Ei/T) Simulation 2 : implementation of cooling, re-using rapid cooling programs : T (t) = T0/(1 t) T dropped to 0.01 from 1000 and, according to the rules updated network state when T = 0.01 at the end of cooling, let T at 0.01 for the 1000 state tran

炉温模糊控制的一般性程序，可以修改各参数从而更改模糊控制表-Temperature control of the general procedures can be amended so as to change the parameters of fuzzy control Table

英国Sheffield大学遗传算法函数包，可节省遗传算法函数开发-Sheffield University United Kingdom function genetic algorithm package, can save the development of genetic algorithm function

这是个神经网络工具箱的一点MATALAB 程序-This is a neural network toolbox 1:00 MATALAB procedures

C++实现神经网路的bp算法，初学者可以参考下 BP algorithm of neural network s achievement based on c++, maybe it is useful to a new learner-C++ Realization of bp neural network algorithm, beginners can refer to under the BP algorithm of neural network s achievement based on c++, Maybe it is useful to a new learner

这是一篇美国博士毕业设计的论文，是用神经网络实现mppt的方案-This is a graduation project of the United States, Dr. thesis, is to use neural network program to achieve MPPT