搜索资源列表
KMeanIntroduction
- 聚类分析是将集合中的数据按其相似性大小分成不同类别的一种方法,它是模式 识别中多变量无监督学习的一个分支,己成功地用于医学,地质,财务,工程,图像 处理和文档等的数据分类中；含有实现此算法的源码 -cluster analysis is to pool the data according to similar size into a different category, It is pattern recognition
JAVAclustering
- JAVA 本程序所实现的功能为对数据进行无监督的学习，即聚类算法-JAVA the procedures for the functions of data unsupervised learning, clustering algorithm
Medoidshift
- 中心点漂移是一种非监督聚类算法（与k-means算法相似，但应用范围更广些),可用于图像分割，基于Matlab实现的源码。 MedoidShift is a unsupervised clustering algorithm(similar to k-means algorithm, but can be used in border application fields), can be used for image segmen
som
- 神经网络中的无监督学习中的SOM学习算法，并在MFC中以主观方式显示学习过程。-Neural network unsupervised learning of SOM learning algorithm, and in MFC in order to show the subjective learning process.
ufc
- ufc无监督优化模糊聚类用于彩色图像分割-ufc Unsupervised Fuzzy Clustering for Color Image Segmentation
apcluster
- 无监督聚类算法,能够自动聚类,不必预先给出类数,聚类精度好于常用的聚类算法.-Unsupervised clustering algorithm, can automatically cluster, do not have to give in advance the number of categories, clustering accuracy of better than commonly used clustering al
RX
- 此算法使用于单波段或者多波段图像中的非监督异常检测，性能很好~-The algorithm used in single-band or multi-band image unsupervised anomaly detection, performance very good ~
hddc_toolbox_1.0
- The High Dimensional Data Clustering (HDDC) toolbox contains an efficient unsupervised classifiers for high-dimensional data. This classifier is based on Gaussian models adapted for high-dimensional data. Referenc
Texture_Segmentation_Diffusion_Feature_Space
- 数字图像处理中的散度特征空间中的无监督的图像纹理分割-Digital image processing in the feature space of divergence Unsupervised texture segmentation of images
fuzzy_c_means
- 本程序用c编写，主要用于对遥感图像进行聚类（非监督分类）。-This programme is used to for clustering images (unsupervised classifciation)
k-means
- kmeans programs to classify data in an unsupervised way
ICM_Unsupervised
- unsupervised icm algorithm for markov random fields.
som(Jal.You)
- SOM神经网络（自组织特征映射神经网络）是一种无导师神经网路。网络的拓扑结构是由一个输入层与一个输出层构成。输入层的节点数即为输入样本的维数，其中每一节点代表输入样本中的一个分量。输出层节点排列结构是二维阵列。输入层X中的每个节点均与输出层Y每个神经元节点通过一权值(权矢量为W)相连接，这样每个输出层节点均对应于一个连接权矢量。 自组织特征映射的基本原理是，当某类模式输入时，其输出层某一节点得到最大刺激而获胜，获胜节点周围的一些节点
spider1
- spider，很好用的模式识别工具箱，里面有各种分类工具，从有监督学习到无监督学习，从模型选择到参数选择。而且也将各个方法封装成类，使用方便。-spider, good use of pattern recognition toolbox, there are various classification tools, from supervised learning to unsupervised learning, choose P
Lecture15-2.Unsupervised-Learning-and-Clustering.
- Unsupervised Learning and Clustering
ISODATA
- ISODATA算法是一种基于统计模式识别的，非常经典的非监督学习动态聚类算法，有较强的实用性。ISODATA算法不仅可以通过调整样本所属类别完成样本的聚类分析，而且可以自动地进行类别的“合并”和“分裂”，从而得到类数比较合理的聚类结果。-ISODATA algorithm is based on statistical pattern recognition, unsupervised learning is the classi
Unsupervised-learning-by-PLSA
- A paper on PLSA title:Unsupervised learning by PLSA
Unsupervised-learningaPLSA-Chinese
- Title：Unsupervised learning by PLSA 概率隐形语义分析学习资料自己翻译的-Title:Unsupervised learning by PLSA It s Chinese Version
Unsupervised-segmentations
- Unsupervised segmentation of color-texture regions in images and video无监督的彩色图像分割方法，非常牛叉-Unsupervised segmentation of color-texture regions in images and video unsupervised color image segmentation method, is very cattle
Unsupervised-intralingual-and-cross-lingual-speak
- Unsupervised intralingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction