c 神经网络遗传算法

this is a program about TSP -this is a program about TSP

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.

这是一个简单的人工智能的例子 希望大家能以此为作出更好的 更完善的

SVM分类器，由上海交通大学编写，软件使用方便、好用-SVM classifier, from the preparation of the Shanghai Jiaotong University, the software easy to use, handy

two Matlab functions for initializing and training a recurrent neural network -two Matlab functions for initializing and training a recurrent neural network

FisherFace, an algorithm based on PCA and LDA

一个bp神经元网络的c++实现，优化了算法，有可执行界面-A bp neural network c++ to achieve and optimize the algorithm, there is an executable interface

采用“提前停止”方法提高 BP 网络的推广能力。对于和例 2相同的问题，在本例中我们将采用训练函数 traingdx -The use of

加了注释的c代码（complexNetwork）源代码，下载后就可以直接使用-Added a comment c code (complexNetwork) source code, downloads can be used directly after

自适应步长BP神经网络训练算法，采用最小误差和梯度下降法更新权值- BP neural network training anaysis， realized by using error feed back, gradient descent applied updating of synaptic weights