搜索资源列表
朴素贝叶斯
- 调用过程 CM = Confusion_matrix(train_predicts, train_targets) [combining_predicts, errorrate] = combining_NB(DP, test_targets, CM) DP,三维数组,(i,j,k)为第k个样本的DP矩阵 targets 为 0 1 2 -process called CM = Confusion_matrix (train_predicts, train_targets) [combining
k_algorithm
- K-均值算法的c语言实现,他是一种基于样本间相似性度量的间接聚类方法。-K-means is a VQ method based on the similarity of the samples. This is a C language source code for K-means algorithm.
一个主要用于预测和分类的源程序
- 开发环境:Matlab 简要说明:程序包含的设置包括:列数、样本总个数、建模样本数、预报因子数、预报对象数、学习因子、 动量因子、训练次数、总体误差、隐节点数。-development environment : Matlab brief descr iption : program includes the installation including : number, the total sample number, the number of samples modeling
模式分类
- 该程序可以对二维三类样本进行分类,并画出分界面.学习过模式识别的人必看.要学习神经网络的人必看,代码简单,实用性强-the procedure three samples of two-dimensional classification and paint interface. Learning the pattern recognition Watchable. To study the neural network Watchable, code simple, practical
广义异或bp算法
- 本文件为用C语言实现的可实现广义异或问题的bp神经网络算法。该问题是对标准异或问题的推广。在标准异或问题中,输入X1和X2取离散量-1或+1,在广义异或问题中,输入(X1,X2)可以在区间[-1,+1] X [-1, +1]内任意取值,而输出为Y=sign(x1,x2),其中sign()为符号函数,在区间[-1,+1] X [-1, +1]内随机产生500个训练样本.本程序用标准BP网实现该分类问题.-this document for the use of C language of achi
Hermit多项式在线学习ran算法
- 本程序用资源分配网(Resource_Allocation Network,简称RAN)实现了Hermit多项式在线学习问题。训练样本产生方式如下,样本数400,每个样本输入Xi在区间[-4,4]内随机产生(均匀分布),相关样本输出为F(Xi) = 1.1(1-Xi + Xi2)exp(-Xi2/2),测试样本输入在[-4,+4]内以0.04为间隔等距产生,共201个样本。训练结束后的隐节点为:11个,训练结束后的平均误差可达:0.03 -this program resources dis
ASM3
- cootes提出的ASM算法的matlab实现。在cootes用于课堂使用的源代码的基础上改写。改正了原来代码中的一些错误,加入了方便使用的样本训练标注保存环节。供图像分析处理,模式识别,人工智能研究者使用。-the ASM Algorithm Implementation of Matlab. Cootes used in the classroom use of the source code on the basis rewritten. To correct the original s
ModularNet
- 本源代码是本人亲自编写的关于模糊神经网络模型的实现,它结合了模糊逻辑和神经网络的优点,具有全局逼近的功能。本代码提供了简单的界面,输入学习样本,可以进行预测并能输出预测结果。-source code is personally prepared by the fuzzy neural network model implementation, which was a combination of fuzzy logic and neural network advantages, and hav
Isodata_algorithm
- ISODATA算法的c++实现, 输入数据保存在data.txt中, 第一行的元素为样本总数sampleNum, 下面每一行为一个样本数据-ISODATA Algorithm c realize that the importation of data stored in data.txt, the first trip to the elements sampleNum the total number of samples, each of the following acts
rbfSrc
- This program demonstrates some function approximation capabilities of a Radial Basis Function Network. The user supplies a set of training points which represent some \"sample\" points for some arbitrary curve. Next, the user specifies the number o
BP_Algorithm719
- 网络为3层结构,输入层为6个神经元,隐含层为4个神经元,输出层为1个神经元,当输入层为中心对称样本 1,0,0,0,0,1等时,网络输出为1,否则输出为0。-network of three-layer structure, input layer to six neurons to the hidden layer 4 neurons, the output layer to a neuron, when the input layer to the center symmetry sampl
KMEANS_FixedBug
- 经典的K均值分类算法源码,修正了原作者没有处理当类中样本为0的情况下的bug-classic K-mean classification algorithm source code, that the original author did not address when the category 0 samples of the bug
FI565
- 内附两个源代码,其中一个源代码是识别程序的,另一个是一个矩阵类库的,所以一并附上。 ~..~因为已经保存了训练好的网络权值,所以第一次使用识别程序时,可以直接运行\\\\Release目录下的可执行文件,然后对图片目录中的测试图片进行读入、识别。 当然读者也可以自行用训练样本训练网络,不过要特别注意训练样本的选择,否则可能造成识别率很低。训练样本选择的原则是,尽可能的有代表性,在训练时间不至于太长的情况下,训练样本数目尽量多。 -containing 2 source code,
BP_recognize_digitV1
- 图像数字的识别。输入一系列有代表性的图像数字的样本,训练网络,得到的权值序列存放到文件中;输入待识别的图像数字序列,通过学习得到的权值矩阵对图像中的数字进行识别,并输出结果。-image recognition. Importation of a representative range of digital images of samples, the training network, the weights of sequences stored to a file; Identifica
p33
- p3随机抽样程序,可随机生成N个服从P3分布的样本.-p3 random sampling procedures, which were randomly generated N obey P3 distribution of the samples.
BP_xor_c
- C语言版的BP算法,解决异或问题!样本需要人为的加入!建一个txt文件就可以了!-C language version of the BP algorithm, resolve differences or problems! The samples were needed to join! built a txt document can!
RBF-nn
- 4输入层,3隐层,2输出层的RBF神经网络分类器 附有测试和训练样本-four input layer, hidden layer 3, the output layer 2 RBF neural network classifiers with testing and training samples
EvolutionaryAlgorithms-2007-06-29
- An evolutionary algorithms application which includes several samples(TSP, Evolution in a 3D fitness landscape, Sudoku)
kmlocal-1.7.1.tar
- 高效的k-means算法实现,使用了k-d树与局部搜索等提高k-means算法的执行效率,同时包含示例代码,用c++代码实现。 Effecient implementation of k-means algorith, k-d tree and local search strategy are implementd to improve the effeciency, samples are included to show how to use it. All codes are imple
HTK-samples-3.3-alpha1.tar
- 隐马尔科夫模型工具箱最新版本使用样本文件,可以广泛应用于识别等领域-HMM Toolbox samples using the latest version of documents can be widely applied in areas such as identification
