条码技术

Autolife模型是一个能够进行“开放式进化”的人工生命系统。每个Agent模型采用可以变化规则表长度的有限自动机模型建模。一方面Agent可以进行自我繁殖，同时模型中的选择机制没有采用显式的适应度函数而是采用能量消耗的简单模型而自发涌现出来，所以可以认为Agent模型是一个类Tierra系统。然而与Tierra、Avida等数字生命模型不同的是，Autolife模型进行了大大的简化，它界面友好，操作直接。虽然没有给每个Agent装配一个虚拟计算机，但是Agent与环境的耦合则可以看成一个图灵机模型，因此Agent可以通过变异而“任意”的编程序。通过Autolife模型，首先人们可以看到一般的生态系统中共存的现象：生物的大爆炸、大灭绝，Agent进化得越来越聪明；其次，用户可以通过变化不同的食物添加规则探索Agent与环境的关系；最后，如果允许Agent通过播种改变环境自动产生食物，那么组织的涌现就是一种不可避免的结果。Agent构成的组织具有自主运动的特性，还可以进行自我修复，可以说Autolife中的组织是一些真正的“活体”。-Autolife model is to conduct an "open-evolution" artificial life system. Each Agent can be used model changes the rules limited the length of the table automatic machine modeling. One Agent can be self-propagation, model selection mechanism not used Explicit the fitness function instead of using the energy consumption of a simple model to emerge spontaneously, so that the agent can be a model category Tierra system. But with Tierra, Avida digital life model is different Autolife model for greatly simplified its

Using Simulated annealing to solve TSP

通过人工神经网络实现异或问题的解决，用visual c++开发-through artificial neural network or differences in the solution of problems with the development of visual c

this about the artificial neural networks which uses the back propogation method.-this is about the artificial neural networks which uses the back propogation method.

用VC做的一个挖掘系统的关联规则算法。COM组件的源代码，已应用到实际系统中。-Utilising VC to make a program which is a arithmetic of affiliated enterprise of dig system. COM components have been applied the system.

SOM人工神经网络的经典例子源代码，是真的

A*算法，用来寻路，非常有用的，我历尽千辛万苦才找到的-A* algorithm, used to find the way, very useful, I experienced a lot of hard work to find the

关于模糊模式识别的最新研究，很有用的资料。-fuzzy pattern recognition on the latest research and useful information.

GENNET是一个通过遗传算法优化权重的16个神经元的全连接神经网络。训练目的是使网络在一定假设的激励下，随时间产生同目标函数同样的响应，即:可以把此网络制作为一个任意波形的信号发生器。 程序分3个示例说明遗传算法进化过程中网络输出的变化趋势。可以看出网络输出（蓝色曲线）随着时间变化逐渐逼近目标函数（红色曲线）。此程序不仅可以学习遗传算法，也可以用于研究全连接网络的直观示例。-GENNET is a genetic algorithm to optimize the weights by the 16 neurons fully connected neural networks. Training purposes is to enable network inspired by certain assumptions, over time, produce the same response with the objective function, namely: the network can be produced as an arbitrary waveform signal generator. Procedure, three examples illustrate the evolution of genetic algorithms in the network output trends. We can see that the network output (blue curve) changes over time, gradually approaching the objective function (red curve). This program can not only learn from the genetic algorithm can also be used to study visual example of a fully connected network.

该源码用来实现基本粒子群的算法，值得参考-The source algorithm is used to achieve the elementary particle group, worth considering