搜索资源列表
randomForest_4.6-7
- Random Forest在R软件上实现，可以更快速的分类，非常实用的方法-Random Forest on the R software, you can more quickly classified, very practical approach
HCgai
- 贝叶斯网络结构学习爬山算法的改进方法，更准确-Improved Bayesian network structure learning climbing algorithm, more accurate
mvrvm_c
- 相关向量机RVM用于预测和分类,含有归一化，训练和测试，可以多变量输出，解决海瑟矩阵问题-RVM relevance vector machine for prediction and classification, containing normalization, training and testing, can be more variable output matrix problem solving Heather
DeepLearning-master
- 深度学习的概念源于人工神经网络的研究。含多隐层的多层感知器就是一种深度学习结构。深度学习通过组合低层特征形成更加抽象的高层表示属性类别或特征，以发现数据的分布式特征表示。[1] 深度学习的概念由Hinton等人于2006年提出。基于深信度网(DBN)提出非监督贪心逐层训练算法，为解决深层结构相关的优化难题带来希望，随后提出多层自动编码器深层结构。此外Lecun等人提出的卷积神经网络是第一个真正多层结构学习算法，它利用空间相对关系减少参数数目以提高训练性能。[1] 深度学习是机器
CELF
- CELF算法是一种比较经典的社会网络影响最大化发现算法，算法的数据结构是采用邻接表-CELF algorithm is a kind of more classic social network influence maximization algorithm, algorithm of adjacency list data structure is adopted.
Adaboost
- 用于分类，二类甚至多类。AdaBoost是Boosting的提升，功能非常的显著-For classification, Class II even more. Boosting AdaBoost is lift, which is very significant
FPtree
- 数据挖掘中关联规则算法的FPtree算法的Python实现。FPtree算法比apriori算法更擅于处理大规模的数据-Data Mining Association Rules algorithm FPtree algorithm implemented in Python. FPtree algorithm apriori algorithm is more than adept at handling large data
FCBF
- This a one of the data mining algorithm completly made by me. This is based on feature subset selection. One of the popular algorithm of feature selection named Fast Correlation based feature selection algorithm(FCBF).It s complete code is here with
heston-summer-xls
- GAUSS has two electronic help systems, corresponding to the GAUSS pdf manuals (available at http://www.aptech.com). 1. The Command Reference is an easy way to pick up information on commands (as long as they are not deemed obsolete ), and is or
TSP
- 用遗传算法解决旅行商问题，注释比较详尽，便于理解-Solve the traveling salesman problem using genetic algorithms, more detailed notes, easy to understand
mLknnMATLAB
- 本代码主要用了多标签K近邻方法（MLKNN）实现对多标签数据进行分类-This code mainly spent more than a label K-nearest neighbor method (MLKNN) to achieve the multi-label data classification
mixBern
- Just like EM of Gaussian Mixture Model, this is the EM algorithm for fitting Bernoulli Mixture Model. GMM is useful for clustering real value data. However, for binary data (such as bag of word feature) Bernoulli Mixture is more suitable.
DBSCAN
- 密度聚类DBSCAN算法的matlab实现，其中分别有源代码，代码举例和算法PPT，较适合初学者上手学习。-DBSCAN density clustering algorithm matlab implementation, which includes codes, the code examples and algorithms PPT. More suitable for beginners to get started.
cf_matrix-decomposition
- 现在比较常用的一种给予举证分解的协同过滤算法，用于个性化推荐-Now more commonly used as a collaborative filtering algorithm decomposition give evidence for personalized recommendation
cf
- 现在比较常用的一种传统的协同过滤算法，用于个性化推荐 最基础的-Now more commonly used as a traditional collaborative filtering algorithms for the most basic personalized recommendation
CARS_Characteristic-band-extraction
- 特征带提取算法，可以很好地提取有用的频带，结果更为准确，CARS_Characteristic带提取.m为主程序，调用程序中的压缩包。-Feature band extraction algorithm, can be a good extraction of useful bands, the results are more accurate, CARS_Characteristic band extraction.m for the main program, call the progr
366265689itoolbox
- 间隔偏最小二乘算法代码，但要自己先琢磨下才更容易吸收-Interval partial least squares algorithm code, but under their own first to be more easily absorbed
k-means
- java实现kmeans算法，方便数据挖掘相关人员更直观了解整个算法的思想及实现过程-java achieve kmeans algorithm to facilitate data relevant personnel more intuitive understanding of the whole idea of mining algorithms and implementation process
方差分析
- 方差分析又称“变异数分析”，是R.A.Fisher发明的，用于两个及两个以上样本均数差别的显著性检验(ANOVA, also called variance analysis, was invented by R.A.Fisher, which was used to test the significance of the mean difference between two and more than two samples)
alexnet
- ALEXNET较为简单的一种实现，参数调整比较方便，数据容易替换(ALEXNET a simpler implementation, parameter adjustment more convenient, easy to replace the data)