Search - 9-1 9-2

Search - 9-1 9-2 - List

[AI-NN-PR] BP神经网络源程序 DL : 0: 基于C开发的三个隐层神经网络，输出权值、阈值文件，训练样本文件，提供如下函数：1）初始化权、阈值子程序；2）第m个学习样本输入子程序；3）第m个样本教师信号子程序；4）隐层各单元输入、输出值子程序；5）输出层各单元输入、输出值子程序；6）输出层至隐层的一般化误差子程序；7）隐层至输入层的一般化误差子程序；8）输出层至第三隐层的权值调整、输出层阈值调整计算子程序；9）第三隐层至第二隐层的权值调整、第三隐层阈值调整计算子程序；10）第二隐层至第一隐层的权值调整、第二隐层阈值调整计算子程序；11）第一隐层至输入层的权值调整、第一隐层阈值调整计算子程序；12）N个样本的全局误差计算子程序。-C development based on the three hidden layer neural network, the output weights, threshold documents, training sample documents, for the following functions : a) initialization, the threshold subroutine; 2) m learning samples imported subroutine; 3) m samples teachers signal Subroutine ; 4) hidden layer of the module input and output value subroutine; 5) the output layer of the module input and output value subroutine; 6) the output layer to the hidden layer subroutine error of generalization; 7) hidden layer to the input layer subroutine error of generalization; 8) the output layer to the third hidden layer Weight adjustment, the output layer threshold adjustment routines; 9) 3rd hidden layer to the second hidden layer weights adjustment, the third hidden layer threshold adjustment routi
Date : 2025-12-25 Size : 11kb User : 李洋
[AI-NN-PR] Mersad-5.9.5-RC2005.tar DL : 0: RoboCup 2D 仿真组老牌强队Mersad 2005的完整源代码，Mersad-5.9.5 (RoboCup 2005) , Allameh Helli High School (NODET) , Islamic Republic of IRAN-RoboCup 2D Simulation Group Mersad 2005 veteran strong teams complete source code, Mersad- 5.9.5 (RoboCup 2005), Allameh Helli High School (NODET) Islamic Republic of IRAN
Date : 2025-12-25 Size : 219kb User : 刘维超
[AI-NN-PR] GA-BP DL : 0: 《遗传算法--理论、应用与软件实现》配套源程序遗传算法——理论、应用与软件实现》，王小平、曹立明编着西安交通大学出版社 2002年第一版本书全面系统地介绍了遗传算法的基本理论，重点介绍了遗传算法的经典应用和国内外的新发展。全书共分11章。第1章概述了遗传算法的产生与发展、基本思想、基本操作以及应用情况；第2章介绍了基本遗传算法；第3章论述了遗传算法的数学基础；第4章分析了遗传算法的多种改进方法；第5章初步介绍了进货计算理论体系；第6章介绍了遗传算法应用于数值优化问题；第7章介绍了遗传算法应用于组合优化问题；第8章介绍了遗传算法应用于机器学习；第9章讨论了遗传算法在智能控制中的应用；第10章讨论了遗传算法与人工生命研究的相关问题；第11章介绍了遗传算法在图像处理、模式识别中的应用。-"genetic algorithm-- the theory, application and software" complementary source of genetic algorithms-- theory, Application and software, "Wang Xiaoping, Li-Ming Cao compile Xi'an Jiaotong University Press in 2002 the first book version of the comprehensive and systematic introduction of the genetic algorithm's basic On focuses on the classical genetic algorithm use and the new development. The book is divided into 11 chapters. Chapter 1 provides an overview of the genetic algorithm for the selection and development of basic ideas, basic operation and the application; Chapter 2 introduces the basic genetic algorithms; Chapter 3 of the genetic basis of a mathematical algorithm; Chapter 4 Analysis of the genetic algorithm approach to improve the variety; Chapter 5 on
Date : 2025-12-25 Size : 677kb User : zhoulu
[AI-NN-PR] 9gong DL : 0: 实现9宫图的自动解，使用了A*寻路算法。-Palace Figure 9 to achieve the automatic solution, use the A* pathfinding algorithm.
Date : 2025-12-25 Size : 408kb User : VicentGuo
[AI-NN-PR] cluster-2.9 DL : 0: Andreas Stolcke开发的聚类源码, 版本2.9。聚类方法是层次合并聚类，同时使用了主成份分析转化向量空间。-Andreas Stolcke developed cluster source, version 2.9. Clustering method is the combined level of clustering, while the use of principal component analysis transformation vector space.
Date : 2025-12-25 Size : 34kb User : eric
[AI-NN-PR] NN+GA DL : 0: 1,改进BP神经网络在股市预测中的应用.2,基于MATLAB工具箱的开采煤层自燃危险性预测.3,基于改进的神经网络的电力系统负荷预报.4,基于神经网络的灌溉用水量预测.5,基于遗传算法改进BP网络的地表沉陷预计.6,利用遗传算法改进BP学习算法.7,模糊神经网络在电力市场短期负荷预测中的应用.8,神经网络学习算法存在的问题及对策.9,遗传神经网络在电力系统短期负荷预测中的应用.10,应用改进BP神经网络进行用水量预测.11,用遗传算法改进的BP模型在刹车系统诊断中的应用研究.12,遗传算法改进的BP神经网络对汛期三门峡水库泥沙冲淤量的计算13,基于遗传算法的人工神经网络学习算法14.自适应遗传算法优化管网状态估计神经网络模型.15,基于GA_RBF神经网络的电梯交通流模式识别的研究-Improved BP Neural Network in Stock Market Prediction
Date : 2025-12-25 Size : 721kb User : 军军
[AI-NN-PR] 5.9 DL : 1: 这个程序是一个六子棋对弈引擎，采用六子棋标准对弈协议，在对弈平台下可以实现人机对弈或者程序间对弈。具有较好的棋力。-This procedure is a sub-six chess game engine, the use of six sub-standard chess game agreement, in the game platform can be achieved between man-machine chess game or program.棋力good.
Date : 2025-12-25 Size : 2.91mb User : 谢汪益
[AI-NN-PR] Workpiecefeatureextraction DL : 0:  1、有9个工件图像，要求从本章讲授的特征提取方法中，选择3~5种提取工件特征并给出数字结果；链码为必选方法，给出数字结果和图形显示，做到链码和原图像的双向变换显示。（实验报告中应描述相应的特征提取方法并略述实现过程）  2、设计的界面中要具备功能：任选1个工件作为目标，以上述实现的特征提取方法识别该目标的工件类型（即序号），并显示该判别基准特征的数据。  3、有可能的话试用聚类、训练或其他方法对这些工件进行分类。 -err
Date : 2025-12-25 Size : 3.54mb User : 苏朗
[AI-NN-PR] Romberg DL : 0: (1) 设计算法并编制程序，进行调试。 (2) 用调试好的程序解决如下问题：计算的近似值，取精度为步骤一、先编制计算函数值的程序；步骤二、执行编制好的Romberg算法，输出T。 (3)用Romberg算法和复合Simpson公式分别计算的近似值，其中b分别取为b=0.1, 0.3, 0.5, 0.7, 0.9 -(1) the design of algorithms and programming, for debugging. (2) with good debugging procedures for the settlement of the following questions: the calculation of the approximation, for the steps to check the accuracy of a first function of the preparation of the calculation procedure step II, the implementation of the preparation of good Romberg algorithm, the output T. (3) using Romberg algorithm and composite Simpson formula for calculating the approximation, respectively, of which b respectively for b = 0.1, 0.3, 0.5, 0.7, 0.9
Date : 2025-12-25 Size : 2kb User : 雯雯
[AI-NN-PR] FLCH3eg1 DL : 0: 采用单神经元结构对两类样本进行分类，其中X为输入样本，T为目标向量。X=[-0.5,-0.5,0.3,0.1,-0.1,0.8,0.2,0.3 0.3,-0.2,-0.6,0.1,-0.5,1.0,0.3,0.9] T=[0,0,0,1,0,1,1,1]- The self learning function of the multilayer perceptron of an artificial neural network can be easily realized by the dynamic change of weights, but it is very difficult to achieve such a change in practice.
Date : 2025-12-25 Size : 1kb User : wlg
[AI-NN-PR] include DL : 0: 用遗传算法解根号2，求根号2，也就是求方程f(x)=x*x-2=0的正整数解，x=1时f(1)<0，x=2时f(2)>0，由介值定理，则1到2中间存在一个根，根据代数基本定理和根的对称性知这就是我们要找的根（废话，初中生都知道是1.414左右），由目标函数得到适应度函数，我们选择个体都在[1,2]之间，那适应度函数我可以取 j(x)=40/(2+|x*x-2|)-10，由x的取值范围知j的范围是(0,10) x和y交叉就用取平均(x+y)/2，交叉概率取0.9，变异概率为0，-Using genetic algorithm for solving square root of 2, Roots, No. 2, that is, of equation f (x) = x* x-2 = 0 the positive integer solution, x = 1 Shi f (1) < 0, x = 2 Shi f (2) " 0, by the intermediate value theorem, then there is a 1-2 middle of the root, according to the fundamental theorem of algebra and the symmetry of the root to know that is what we are looking for the root (nonsense, junior high school students all know that 1.414 or so), from the target function to fitness function, we have chosen to individuals are in [1,2] between the fitness function that I can take j (x) = 40/(2+ | x* x-2 |)-10, from the x' s j known range of the range is (0,10) x and y cross on the use of taking the average (x+ y)/2, taking 0.9 crossover probability, mutation probability of 0,
Date : 2025-12-25 Size : 3kb User : yuxin
[AI-NN-PR] kohonen DL : 0: This program is a simple demonstration of a Kohonen self-organizing neural network. The program merely maps itself to a set of coordinates ranging from -0.5 to 0.5 on both the x and y-axis. The program layout is very simple - the Run button will start the network. Note, this may take some time, so be patient! Note that phase is shown in the title bar. The two edit controls at the right are the Phase 1 (top) and Phase 2 (bottom) iterations. Alter these values to see how it affects the learning of the program. During Phase 1, the learning coefficient, k, goes from 0.9 to 0.01, linearly decreasing with the iterations. The neighbourhood, Nx is set at half the diameter of the net, and also linearly decreases. During Phase 2, k decreases from 0.1 to 0.0, with Nx fixed at 1.-This program is a simple demonstration of a Kohonen self-organizing neural network. The program merely maps itself to a set of coordinates ranging from-0.5 to 0.5 on both the x and y-axis. The program layout is very simple- the Run button will start the network. Note, this may take some time, so be patient! Note that phase is shown in the title bar. The two edit controls at the right are the Phase 1 (top) and Phase 2 (bottom) iterations. Alter these values to see how it affects the learning of the program. During Phase 1, the learning coefficient, k, goes from 0.9 to 0.01, linearly decreasing with the iterations. The neighbourhood, Nx is set at half the diameter of the net, and also linearly decreases. During Phase 2, k decreases from 0.1 to 0.0, with Nx fixed at 1.
Date : 2025-12-25 Size : 176kb User : Luigi
[AI-NN-PR] libsvm-weights-2.9 DL : 0: 数据属性的权重分析. 用户可以给每个数据实例权重-Weights for data instances Users can give a weight to each data instance.
Date : 2025-12-25 Size : 48kb User : quarryhero
[AI-NN-PR] libsvm-2.9 DL : 0: libsvm-2.9，svm的基本程序，台湾人编写的，是学习理解模式识别比较重要的调试程序。-libsvm-2.9, svm basic procedures, written in Taiwanese, is more important to learn to understand pattern recognition debugger.
Date : 2025-12-25 Size : 524kb User : xue
[AI-NN-PR] BP-neural-network_c DL : 0: 基于C开发的三个隐层神经网络，输出权值、阈值文件，训练样本文件，提供如下函数： 1）初始化权、阈值子程序； 2）第m个学习样本输入子程序； 3）第m个样本教师信号子程序； 4）隐层各单元输入、输出值子程序； 5）输出层各单元输入、输出值子程序； 6）输出层至隐层的一般化误差子程序； 7）隐层至输入层的一般化误差子程序； 8）输出层至第三隐层的权值调整、输出层阈值调整计算子程序； 9）第三隐层至第二隐层的权值调整、第三隐层阈值调整计算子程序； 10）第二隐层至第一隐层的权值调整、第二隐层阈值调整计算子程序； 11）第一隐层至输入层的权值调整、第一隐层阈值调整计算子程序； 12）N个样本的全局误差计算子程序。 -BP neural network，VC 6.0
Date : 2025-12-25 Size : 11kb User : Melo Wong
[AI-NN-PR] Neural-network-qiduanma DL : 1: 设用7个短线段构成1,2,3,4,5,6,7,8,9,10共10个数码图形，令这7个线段分别用一个矢量来代表，又设对数码图形中用到的线段，相应分量取值为1，未用到的线段相应的分量取值为0，因此每个数码图形分别可由一个矢量表示，其顺序编号为：，试设计一神经网络，能够区分奇数码和偶数码。-Set with seven short line segments 1, 2, 3, 4, 5, 10 digital graphics, 7 segment represented by a vector, and digital graphics used in the segment, the corresponding component value of 1, and the unused segments corresponding component value of 0 can be a vector, respectively, so that each digital graphics, its sequence number is: trial design of a neural network, it is possible to distinguish the odd and even digital.
Date : 2025-12-25 Size : 1.03mb User : 楼宇舟
[AI-NN-PR] firstorder DL : 0: 人工智能，一阶逻辑化子句集问题的9步法求解，可显示每步的结果，C#的winForm程序-Artificial Intelligence, 9 first-order logical step to solve the problem clause set can display the results of each step, C# program of winForm
Date : 2025-12-25 Size : 88kb User : Changcheng
[AI-NN-PR] self DL : 0: 实现0-9的自联想以及A-J异联想的人工神经网络，c#代码编写-neural network
Date : 2025-12-25 Size : 134kb User : symphere
[AI-NN-PR] PatternRecognition DL : 0: (1)Bayes分类已知N=9， =3，n=2，C=3,问x= 应属于哪一类？ (2)聚类使用c－均值聚类算法在IRIS数据上进行聚类分析 (3)鉴别分析在ORL或Yale标准人脸数据库上完成模式识别任务。用PCA与基于核的PCA（KPCA）方法完成人脸图像的重构与识别试验。-(1) Bayes classification Known N = 9, = 3, n = 2, C = 3, x = should ask which category? (2) Cluster C-means clustering algorithm using cluster analysis on IRIS data (3) discriminant analysis Pattern recognition tasks completed on ORL face database standard or Yale. With PCA and nuclear-based PCA (KPCA) method to complete the reconstruction of the face image recognition test.
Date : 2025-12-25 Size : 7kb User : 刘宏
[AI-NN-PR] pHash-0.9.4-sourcecode DL : 0: 开源的图像相似度感知hash算法，支持jpg等主流图像的相似度匹配。-the sourcecode algrithm is about picture of perceptual hash, supporting jpg format, and so on.
Date : 2025-12-25 Size : 513kb User : 王易之

« 12 3 4 »