搜索资源列表
MD5suanfaJavaBeanMD5
- MD5算法Java BeanMD5，希望大家参考学习，相信您会有所收获-Java BeanMD5 MD5 algorithm, we hope to learn information, I believe that you will gain
C4.5算法源程序
- C4.5算法进行决策树生成 以信息增益最大的属性作为分类属性，生成决策树，从而得出决策规则。-C4.5 decision tree algorithms to generate information gain the greatest attribute as a classification attributes, generate decision tree, and came to decision-making rules.
C4_5.m
- his algorithm was proposed by Quinlan (1993). The C4.5 algorithm generates a classification-decision tree for the given data-set by recursive partitioning of data. The decision is grown using Depth-first strategy. The algorithm considers all the poss
ID3
- The algorithm ID3 (Quinlan) uses the method top-down induction of decision trees. Given a set of classified examples a decision tree is induced, biased by the information gain measure, which heuristically leads to small trees. The examples are given
matlab_Lab3
- information gain calculation in Matlab
ParInfoGain
- ParInfoGain - Computes parallel information gain and gain ratio in Matlab using the Matlab Parallel Computing Toolbox or the Distributed Server (if available) Information gain is defined as: InfoGain(Class,Attribute) = H(Class) - H(Class | At
TestID3
- 决策树算法部分代码（从文件中读数据并计算信息增益）-Part of the code of the decision tree algorithm (data read from the file and calculate the information gain)
onTextCategorization
- 本文比较研究了在中文文本分类中特征选取方法对分类效果的影响。考察了文档频率DF、信息增 益IG、互信息MI、V2分布CHI 四种不同的特征选取方法。采用支持向量机(SVM) 和KNN两种不同的分类 器以考察不同抽取方法的有效性。实验结果表明, 在英文文本分类中表现良好的特征抽取方法( IG、MI 和 CHI)在不加修正的情况下并不适合中文文本分类。文中从理论上分析了产生差异的原因, 并分析了可能的 矫正方法包括采用超大规模训练语料和采用组合的特征抽取方法。最后通过实验验证组合特征
C4.5
- 决策树分类 通过读取数据 求信息增益率选择最好的分离属性-Decision tree classification by reading the data and information gain ratio to select the best separation properties
informationgain
- 完全的信息增益比代码，有注释。已运行。可进行信息熵，信息增益运算-Complete information gain ratio code, annotated.
DecisionTreeID3
- 决策树ID3算法的MATLAB程序，这里采用信息增益的方法.-MATLAB program of Decision Tree Algorithm ID3，by the information gain.
InformationGain
- 使用java实现的信息增益算法，附带了一些训练样本，已经进行了分词-Java algorithm using information gain realized, with some training samples have been carried out participle
c4.5
- C4.5是机器学习算法中的另一个分类决策树算法,它是基于ID3算法进行改进后的一种重要算法,相比于ID3算法,改进有如下几个要点:用信息增益率来选择属性.-C4.5 decision tree algorithm is another classification machine learning algorithm, which is based on ID3 algorithm is an important algorithm improved, compared to the ID3 a
InformationGain
- 全部信息熵的计算，包括信息熵，条件信息熵以及信息增益。附带Andrew的信息增益教程-All information entropy calculations, including information entropy, conditional entropy and information gain. Andrew incidental information gain Tutorials
TextureClassification_NonExtensiveEntropy
- Non-Extensive entropy with Gaussian Information Gain for identifying and classifying regular textures which contain repetitive patterns correlated over space that translates to high probabilities in the gray level co-occurrence matrix-Non-Extensive e
ID3
- MATLAB下的决策树ID3算法，应用信息增益来划分节点-ID3 decision tree algorithm under MATLAB application information gain to divide the node
treePlotter
- 决策树根据信息增益对数据进行分类，并且构造树的结构，输出结果易于理解-Decision tree based on information gain to classify the data, and construct the structure of the tree, the output result is easy to understand
DecisionTreeID3
- ID3算法是一种贪心算法，用来构造决策树。ID3算法起源于概念学习系统（CLS），以信息熵的下降速度为选取测试属性的标准，即在每个节点选取还尚未被用来划分的具有最高信息增益的属性作为划分标准，然后继续这个过程，直到生成的决策树能完美分类训练样例。(The ID3 algorithm is a greedy algorithm, which is used to construct a decision tree. ID3 algorithm originated from the concept
决策树与随机森林
- 给出对决策树与随机森林的认识。主要分析决策树的学习算法：信息增益和ID3、C4.5、CART树，然后给出随机森林。 决策树中，最重要的问题有3个: 1. 特征选择。即选择哪个特征作为某个节点的分类特征； 2. 特征值的选择。即选择好特征后怎么划分子树； 3. 决策树出现过拟合怎么办？ 下面分别就以上问题对决策树给出解释。决策树往往是递归的选择最优特征，并根据该特征对训练数据进行分割。(The understanding of decision tree and random
jiqixuexi
- 编写代码计算信息增益，splitDataSet函数是用来选择各个特征的子集的，比如选择年龄(第0个特征)的青年(用0代表)的自己，我们可以调用splitDataSet(dataSet,0,0)这样返回的子集就是年龄为青年的5个数据集。chooseBestFeatureToSplit是选择选择最优特征的函数。(Write code to calculate the information gain.SplitDataSet function is used to select the featur