这是一篇对PSO算法可以使用从事人工智能的学生…

神经网络算法

遗传算法的matlab实现，举例说明遗传算法的基本实现步骤，适用于初学者-Matlab genetic algorithm to achieve, for example, shows the basic implementation steps of genetic algorithm is suitable for beginners

这个是matlab的BP 神经网络-This is matlab" s BP neural network. . . . . . . . . . . . .

神经网络全部源代码-neural network full source code

遗传算法简称GA(Genetic Algorithm)，在本质上是一种不依赖具体问题的直接搜索方法。遗传算法在模式识别、神经网络、图像处理、机器学习、工业优化控制、自适应控制、生物科学、社会科学等方面都得到应用。在人工智能研究中，现在人们认为“遗传算法、自适应系统、细胞自动机、混沌理论与人工智能一样，都是对今后十年的计算技术有重大影响的关键技术”。-Referred to as genetic algorithm GA (Genetic Algorithm), in essence is a kind of do not rely on specific issues of direct search method. Genetic algorithm in pattern recognition, neural networks, image processing, machine learning, optimization of industrial control, adaptive control, biological sciences, social sciences and so on have been applied. Research in artificial intelligence, now that the " genetic algorithms, adaptive systems, cellular automata, chaos theory and artificial intelligence, are the next ten years of the computing technology have a major impact on the key technology."

自主式决策树学习的程序源码，对研究机器学习的同行很有用。-Autonomous Decision Tree learning procedures source, the study machine learning peer useful.

能准确计算lyapunov-Exponent 来判断一个系统是不是混沌系统-Can accurately calculate the lyapunov-Exponent to determine a system is chaotic systems

一篇关于遗传算法组卷的论文，论文中详尽的描述了遗传算法用于组卷的关键技术-A paper on genetic algorithm test paper, paper, a detailed description of the genetic algorithm for the key technologies Test Paper

可拓学的专家系统,基于B/S结构,动态,网络专家系统.-Extenics expert system, based on B/S structure, dynamics, network expert system.

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.