关于人工神经网络的实用书籍，适合初学者，以及有一定基础的读者学习...

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.

本文件为遗传算法的工具箱，包括遗传算法的各种选择、交叉、变异等算法。-This document is for the genetic algorithm toolbox, including a variety of genetic algorithm selection, crossover, mutation and other algorithms.

该软件通过BP神经网络学习机制，能够对屏幕上的数字进行识别。-the software through BP neural network learning mechanism, to right on the screen digital identification.

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

MATHEMATICA 软件运用 The biggest similarity for tsp-MATHEMATICA software to use The biggest similarity for tsp

支持向量机(SVM)的VC源代码，内有应用手册和应用实例。-Support Vector Machine (SVM) of the VC source code, with the application of manuals and application examples.

模式识别的源代码，针对大样本集中样本自动分类的程序，可以手动控制输入点！-pattern recognition source code, sample concentration on large samples of automatic classification procedure can be controlled manually input!

本文采用红外光电传感器技术, 建立了一个基于神经网络的客流计数系统, 与传 统的仅利用光电传感器计数方法相比, 该方法提高了实时客流计数准确率。为了更好的分 类识别计数, 针对采集的连续的时空序列客流数据特点, 改进了已有的分割方法和针对客 流实际情况的特征提取方法。最后经过稀疏和密集客流模拟仿真测试, 结果表明, 本文所 提出的模型能够识别多人并排的情况, 误差率较低, 具有理论和实际意义。-RBF

贝叶斯方法在房地产风险决策中的应用研究.pdf-TheApplicationofBayesMethodtoRealRiskDecisionMaking

isomap等规度映射，特征提取，机器学习-Isotacticity isomap mapping, feature extraction, machine learning