Genetic algorithm to initialize the network weights and threshold parameters imp...

使用遗传算法求解通信网链路容量和流量联合优化分配问题!-Communications network using genetic algorithm for solving the joint optimization of link capacity and flow allocation problem!

无先导粒子滤波器工具箱，并附带pf，kf，Ukf程序，用于跟踪估计-without leading particle filter toolbox and fringe pf, kf, Ukf procedures for tracking estimates

神经网络C程序的第6章-neural network C procedures for the Chapter 6

Hopfield 网――擅长于联想记忆与解迷路 实现H网联想记忆的关键，是使被记忆的模式样本对应网络能量函数的极小值。 设有M个N维记忆模式，通过对网络N个神经元之间连接权 wij 和N个输出阈值θj的设计，使得: 这M个记忆模式所对应的网络状态正好是网络能量函数的M个极小值。 比较困难，目前还没有一个适应任意形式的记忆模式的有效、通用的设计方法。 H网的算法 1）学习模式――决定权重 想要记忆的模式，用-1和1的2值表示 模式：-1，-1，1，-1，1，1，... 一般表示： 则任意两个神经元j、i间的权重： wij=∑ap(i)ap(j)，p=1…p； P：模式的总数 ap(s)：第p个模式的第s个要素（-1或1） wij：第j个神经元与第i个神经元间的权重 i = j时，wij=0，即各神经元的输出不直接返回自身。 2)想起模式： 神经元输出值的初始化 想起时，一般是未知的输入。设xi(0)为未知模式的第i个要素（-1或1） 将xi(0)作为相对应的神经元的初始值，其中，0意味t=0。 反复部分：对各神经元，计算： xi (t+1) = f (∑wijxj（t）-θi), j=1…n, j≠i n―神经元总数 f（）--Sgn（） θi―神经元i发火阈值 反复进行，直到各个神经元的输出不再变化。-Hopfield network-- good at associative memory solution with the realization of lost H associative memory networks, are key to bringing the memory model samples corresponding network energy function of the minimum. With M-N-dimensional memory model, the network N neurons connect between right wij and N output threshold j design makes : M-mode memory corresponding to the network is a state network energy function is the M-000 minimum. Mor

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

结合均匀设计表和小边经验公式产生初始种群，使TSP应用遗传算法能求出更优更快解，详尽说明见paper.doc。-uniform design combining a small side table and have empirical formula initial population, TSP application of genetic algorithms can be obtained faster and better solutions, detailed description of paper.doc.

连续型粒子群算法的java实现，可以自己设计粒子群算法（继承Swarm和Particle类），包含有三个个抽象类（Swarm、Particle、Problem），可以继承Problem类自定义新的问题。-continuous particle swarm algorithm to achieve the java can design their own PSO algorithm (inheritance and Particle Swarm), contains an abstract category 3 (Swarm, Particle, Problem), can be inherited from the definition of Class Problem new problems.

matlab实现，附带数据，并有显示结果图的功能，很方便用的-It s implemented using matlab with data as attachment. It also has the function of showing the result and is very convenient to use.

本代码用基于steve语言的breve软件编写的，此软件是一种3D人工智能的环境模拟器，可以用来构建AGENT-BASED SYSTEM和模拟机器人行为。本代码实现功能如下：机器人服务模拟。自动取得饮料，递送给客人，客人喝完后，另一种清理机器人处理瓶子并运送垃圾堆。主要为了证明机器人运动中的一种Deliberative设计结构。软件下载地址：http://www.spiderland.org/breve/download.php 打开我上传的文件后，点运行就可以看效果。-The code-based software steve language breve prepared, the artificial intelligence software is a 3D environment simulator can be used to build the AGENT-BASED SYSTEM and robot behavior simulation. Realize this function code is as follows: service robot simulation. Automatically beverages, delivered to the guests, the guests after the finish, another robot cleaning up the bottle and the delivery of garbage treatment. Mainly in order to prove that the movement of a robot design structure Deliberative. Software Download: http://www.spiderland.org/breve/download.php open my uploaded file, you can look at the effect of running.

matlab小程序，为初学者提供一些常用的例子-There provide some basic matlab programs that will help a biginer a lot.