在国外网站上下的关于神经网络的原理理解原码

MCRGSA------组播路由问题遗传模拟退火算法 ％M-----------遗传算法进化代数 ％N-----------种群规模，取偶数 ％Pm----------变异概率调节参数 ％K-----------同一温度下状态跳转次数 ％t0----------初始温度 ％alpha-------降温系数 ％beta--------浓度均衡系数 ％ROUTES------备选路径集 ％Num---------到各节点的备选路径数目 ％Cost--------费用邻接矩阵 ％Source------源节点标号 ％End---------目的节点标号组成的向量 ％MBR---------各代最优路径编码-MCRGSA------ Multicast Routing genetic simulated annealing% M----------- genetic algorithm algebra% N----------- population size, even take Pm----------% probability parameter variation%----------- same temperature K Jump under a number of state----------% t0 initial temperature cooling% alpha------- beta coefficient%-------- balanced concentration coefficient% ROUTES------ Alternative Path Set% Enable--------- nodes to the number of alternative paths%-------- Cost adjacent costs Matrix% Source------ source node labeling% End--------- destination node labeling Group Vector%% of the MBR--------- generations optimal path coding

Fast ICA，一种ICA的快速算法，有完整的论文（两种格式，pdf和ps的）-Fast ICA, the ICA a fast algorithm, a complete paper (both formats, pdf and ps)

lzb的程序示例,方便修改,适合初学者使用!-lzb sample procedures to facilitate the modification, suitable for beginners to use!

蚁群算法及其在TSP中的应用。一篇很好的论文。-Ant colony algorithm and its application in the TSP. A very good paper.

这个是遗传算法的PPT讲义 很有帮助 大家可以看看 -This is a genetic algorithm PPT helpful lectures we will look at the

自组织系统Kohonen网络模型。对于Kohonen神经网络，竞争是这样进行的：对于“赢”的那个神经元c，在其周围Nc的区域内神经元在不同程度上得到兴奋，而在Nc以外的神经元都被抑制。网络的学习过程就是网络的连接权根据训练样本进行自适应、自组织的过程，经过一定次数的训练以后，网络能够把拓扑意义下相似的输入样本映射到相近的输出节点上。网络能够实现从输入到输出的非线性降维映射结构：它是受视网膜皮层的生物功能的启发而提出的。~..~-Kohonen network model. For Kohonen neural network, competition is this : For the "winner" of neurons c, in its switching around the region neurons in varying degrees, to be excited, and the switching outside the neurons were inhibited. Network learning is a process in the network connecting the right under the training samples for adaptive, self-organizing process, after a certain number of training, network topology can sense similar to the mapping of the input samples similar to the output nodes. Network can be achieved from input to output of nonlinear reduced-dimensional mapping structure : it is subject to retinal cortex of the biological function inspired by. ~ ~ ..

包括883分酒问题，图的遍历等人工智能基本算法-Including 883 hours of liquor problem, artificial intelligence, such as graph traversal algorithm

多目标优化进化算法目前公认效果收敛性最好的算法NSGA2源码，内有多目标算法的工具箱，对实现其他多目标优化算法很有帮助-Multi-objective optimization evolutionary algorithm is currently recognized as the effect of convergence of the algorithm NSGA2 best source, with a number of target algorithm toolbox for achieving the other multi-objective optimization algorithm for helpful

SVM模式识别技术及在机械故障诊断中的应用进展-SVM pattern recognition technology and in Mechanical Fault Diagnosis of progress

LVQ(学习矢量量化)算法：它是Kohonen的有监督学习的扩展形式。融合了自组织和有导师监督的技术，学习方法是竞争的，但产生方式是有教师监督的，也就是说，竞争学习是在由训练输入指定的各类中局部进行。-LVQ (LVQ) algorithm : it is Kohonen of supervised learning the expansion of the form. The convergence of self-organization and supervision of the instructors, learning methods of competition, but there are ways teachers to supervise, meaning that the competitive learning is the training input from the designated categories of partial.