fortran 语 言 编 写 基 本 遗 传 算 法 源 程 序 fortran Genetic Algorithms written by FORTRAN...

matlab在神经网络中的一些界面函数-Matlab in neural network interface function of

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

Joone神经网络开源－－框架完全手册，但是，是英文的。不过很值得一看，-Joone neural network revenue- the framework of full manual, however, is English. But it is worth a visit,

BP神经网络算法，可以调节隐层，输入输出等-BP neural network algorithm, can be adjusted hidden layer, input and output, etc.

对于学习混沌理论的人很有用的，这也是搜集到的-Chaos Theory for the study were very useful, which is collected

一个关于指向插补和曲线插补的程序，本程序有一个菜单可以选择，曲线插补是哦可以选择是顺时针或者逆时针-On the point interpolation and curve interpolation procedure, this procedure can select a menu, curve interpolation is to choose Oh, is clockwise or counter-clockwise

This software was done in part for a textbook on AI I ve written called _The Basis of AI_ (tentative title, subject to change but not if I get my way). For details see: http://www.mcs.com/~drt/basisofai.html

使用clips解决4人限定时间过河问题。附带clips源代码。-use clips resolve four limit the time the river issues. Fringe clips source code.

八数码难题求解程序本程序所采用的启发函数,本人不能证明它能解决任何的八数码难题,如果对于较难的问题会产生很多节点,有可能会使空间不足,所以尽量不要出太难的问题难为它.希望广大的人工智能爱好者能写出更好的启发函数.-eight digital problem solving program of the procedures used by the heuristic function, I can not prove that it can resolve any of the eight digital problem, if for the more difficult problems will have many nodes, it is likely to lack of space, so as not up to the difficult problems it hard. I hope the love AI who better to write a heuristic function better.

一种新型模糊形态神经网络及其应用研究,比较有参考意义-fuzzy form a new neural network and its applied research, more reference value