神经网络基本算法源程序，包含四个基本算法：BF,ART I,RBF,自组织算法，有详细的帮助文件。
basic neural network algorithm source, contains four basic arithmetic : BF, ART I, RBF, self-organizing algorithm, a detailed help files. (2005-04-15, Visual C++, 143KB, 下载514次)
几篇最经典的运动搜索算法的IEEE论文：A1. Enhanced Hexagonal Search for Fast Block Motion Estimation；A2. Hexagon-based search pattern for fast block motion estimation；A3. Predictive Motion Vector Field Adaptive Search Technique (PMVFAST)等
A few classic sports search algorithm IEEE papers: A1. Enhanced Hexagonal Search for Fast Block Motion Estimation A2. Hexagon-based search pattern for fast block motion estimation A3. Predictive Motion Vector Field Adaptive Search Technique (PMVFAST), etc. (2007-11-14, Others, 7665KB, 下载124次)
Matlab实现BF算法
Matlab algorithms BF (2004-11-07, MultiPlatform, 4KB, 下载67次)
卷积神经网络的c++ 实现版本，本文件主要供学习机器学习的同学使用，里面代码有详细注释
CNN matlab (2015-12-22, Visual C++, 14371KB, 下载48次)
RoboCup 2D 仿真组冠军源代码之1997年冠军队——CMUnited97源代码，这是第一年正式的RoboCup比赛。
RoboCup championship 2D simulation source code's 1997 championship team-- CMUnited 97 source code, which is the first year of formal RoboCup competition. (2007-03-15, Unix_Linux, 179KB, 下载41次)
对具有随机噪声的二阶系统的模型辨识，进行标幺化以后系统的参考模型差分方程为： y(k)=a1*y(k-1)+a2*y(k-2)+b*u(k-1)+s(k) 式中，a1=0.3366,a2=0.6634,b=0.68,s(k)为随机噪声。由于神经网络的输出最大为1，所以，被辨识的系统应先标幺化，这里标幺化系数为5。采用正向建模(并联辨识)结构，神经网络选用3-9-9-1型，即输入层i，隐层j包括2级，输出层k的节点个数分别为3、9、9、1个；由于神经网络的最大输出为1，因此在辨识前应对原系统参考模型标么化处理，辨识结束后再乘以标么化系数才是被辨识系统的辨识结果。
of random noise with the second-order system model, per-unit system after the reference model differential equation : y (k) = y* a1 (k-1) a2* y (k-2) b* u (k-1) s (k)- style, = 0.3366 a1, a2 = 0.6634, b = 0.68, s (k) as random noise. Because the neural network for a maximum output, therefore, the identification system should be per-unit, per-unit here coefficient of 5. Forward modeling (Parallel identification) structure, neural network-based selection 3-9-9-1, i input layer, hidden layer, including two j, k output layer to the number of nodes 3,9,9,1; The neural network the biggest losers up to one, in the original deal before Identification System Reference Model S Mody treatment, then multiplied by the end of Identification Standard Mody coefficient was recognition system is the ide (2005-06-06, C/C++, 854KB, 下载37次)
这是bf求最长公共子列，由于算法比较简单，就是简单的遍历，下次有功夫，把动态规划的算法上传。
this is just a simple lsc problem. (2009-05-10, C/C++, 1KB, 下载36次)
BP网络与RBF径向基网络对比（傻瓜教程，10秒学会神经网络）
BP and RBF NET (2010-10-29, matlab, 74KB, 下载31次)
粗糙度A1， 惯性矩A2，纹理熵A3，相关度A4，方差A5，逆差矩阵A6,纹理特征提取
extract six texture figures (2012-01-06, matlab, 1KB, 下载31次)
cnn Mnist 两层卷积实现，可以达到97%d 识别率，大家可以拿来上手试用
CNN MNIST two layers (2018-04-29, matlab, 4KB, 下载29次)
实现神经网络分类，适用于非侵入式电荷分解
Realization of neural network classification (2018-04-13, matlab, 31298KB, 下载28次)
数字波束形成技术，本文提供常规相移方法产生波束的技术
beam forming (2012-02-28, matlab, 1KB, 下载28次)
神经网络学习，一个好的神经网络学习练习用的入门程序
Neural network learning, a good practice to use neural networks to learn the entry procedures for (2009-10-19, matlab, 1KB, 下载26次)
BF算法实现，Bellman-Ford 网络优化算法，CSPF部署
Bellman-Ford (2009-05-15, Visual C++, 2KB, 下载23次)
BOARD_XMEGA_A1_XPLAINED & RFM23BP
BOARD_XMEGA_A1_XPLAINED & RFM23BP (2014-07-03, C/C++, 15975KB, 下载19次)
人体检测的完整工程（包含测试图片），利用目标检测算法SVM,准确率达到97
Human detection complete works (including test images), the use of the target detection algorithm SVM, accuracy rate of 97 (2017-03-29, Visual C++, 1389KB, 下载18次)
在传统遗传算法的基础上，引入FFD、BF近似算法的思想，提出求解该类问题的混合遗传算法。
In the traditional genetic algorithm, based on the introduction of FFD, BF approximation algorithm ideas put forward to solve such problems of hybrid genetic algorithms. (2011-08-21, matlab, 255KB, 下载18次)
％以FRP－混凝土面内剪切试验说明matlab神经元网络的使用
％读入试验数据，数据格式为
％ FRP厚度(mm) FRP宽度(mm) FRP粘结长度(mm) FRP弹模(GPa) 混凝土抗拉强度(MPa) 混
凝土宽度(mm)
％[ 0.169 50 130 97 2.9 100]
％网络输出为极限承载力
Of FRP-concrete-plane shear test matlab neural network description of the use of read test data, data format FRP thickness (mm) FRP width (mm) FRP bond length (mm) FRP elastic modulus (GPa) Concrete tensile strength (MPa) concrete width (mm) [0.169 50 130 97 2.9 100] network output for the ultimate bearing capacity (2008-05-12, matlab, 67KB, 下载17次)
本侧率主要运用在外汇投资上市用特别欧美品种起到非常不错稳定效果大家可以下载自己进行研究一下。
This side rate is mainly used in foreign exchange investment listing with special European and American varieties play a very good stabilization effect you can download their own research. (2018-10-25, C/C++, 58KB, 下载16次)
SAT问题也称为合取范式的可满足问题，一个合取范式形如：A1∧A2∧…∧An，子句Ai（1≤i≤n）形如：a1∨a2∨…∨ak，其中ai为文字，为某一布尔变量或该布尔变量的非。SAT问题是指：是否存在一组对所有布尔变量的赋值（TRUE或FALSE），使得整个合取范式取指为真。
SAT problem, also known as conjunctive normal to meet a conjunctive normal form: A1 ∧ A2 ∧ ... ∧ An clause Ai (1 ≤ i ≤ n) of the form: a1 ∨ a2 ∨ ... ∨ ak ai to the text, is a Boolean variable or non Boolean variables. SAT problem is: Is there a group assignment of all Boolean variable (TRUE or FALSE), and makes the whole conjunctive normal fetch is true. (2012-11-22, Visual C++, 574KB, 下载14次)