Description: Probabilistic Principal Components Analysis. [VAR, U, LAMBDA] = PPCA(X, PPCA_DIM) computes the principal
％ component subspace U of dimension PPCA_DIM using a centred covariance
matrix X. The variable VAR contains the off-subspace variance (which
is assumed to be spherical), while the vector LAMBDA contains the
variances of each of the principal components. This is computed
using the eigenvalue and eigenvector decomposition of X.-Probabilistic Principal Components Analysis. [VAR, U, LAMBDA] = PPCA (X, PPCA_DIM) computes the principal component subspace U of dimension PPCA_DIM using a centred covariancematrix X. The variable VAR contains the off-subspace variance (whichis assumed to be spherical ), while the vector LAMBDA contains thevariances of each of the principal components. This is computedusing the eigenvalue and eigenvector decomposition of X. Platform: |
Size: 1024 |
Author:西晃云 |
Hits:
Description: Probabilistic Principal Component Analysis
– Latent variable models
– Probabilistic PCA
• Formulation of PCA model
• Maximum likelihood estimation
– Closed form solution
– EM algorithm
» EM Algorithms for regular PCA
» Sensible PCA (E-M algorithm for probabilistic PCA)
– Mixtures of Probabilistic Principal Component
Analysers-Probabilistic Principal Component Analysis
– Latent variable models
– Probabilistic PCA
• Formulation of PCA model
• Maximum likelihood estimation
– Closed form solution
– EM algorithm
» EM Algorithms for regular PCA
» Sensible PCA (E-M algorithm for probabilistic PCA)
– Mixtures of Probabilistic Principal Component
Analysers Platform: |
Size: 263168 |
Author:Tatyana |
Hits:
Description: 应用主成分分析对数据降维，将得到的数据用于概率神经网络训练，进行模式识别。对于一组新数据，先计算主成分得分，再输入训练好的概率神经网络，就会得到识别结果，即改组数据属于何种类别。-Principal component analysis of the data reduction, data will be obtained for the probabilistic neural network training, pattern recognition. For a new set of data, the first principal component scores calculated, then enter the trained neural network, will get the recognition result, that is, the set of data belongs to which category. Platform: |
Size: 2048 |
Author:何晶晶 |
Hits:
Description: 概率原型分析软件，语言matlab，属于数据分析软件，非监督学习方法，类似于PCA,NMF等-Archetypal analysis represents a set of observations as convex combinations of pure patterns, or archetypes.
The original geometric formulation of finding archetypes by approximating the convex hull of the observations assumes them to be real valued. This, unfortunately, is not compatible with many practical situations.
In this paper we revisit archetypal analysis the basic principles, and propose a probabilistic framework that accommodates other observation types such as integers, binary, and probability vectors. We
corroborate the proposed methodology with convincing real-world applications on finding archetypal winter tourists based on binary survey data, archetypal disaster-affected countries based on disaster count data,
and document archetypes based on term-frequency data. We also present an appropriate visualization tool
to summarize archetypal analysis solution better. Platform: |
Size: 14497792 |
Author:tower |
Hits:
Description: 态势要素获取作为整个网络安全态势感知的基础，其质量的好坏将直接影响态势感知系统的性能。针对态势要素不易获取问题，提出了一种基于增强型概率神经网络的层次化框架态势要素获取方法。在该层次化获取框架中，利用主成分分析(PCA)对训练样本属性进行约简并对特殊属性编码融合处理，将其结果用于优化概率神经网络(PNN)结构，降低系统复杂度。以PNN作为基分类器，基分类器通过反复迭代、权重更替，然后加权融合处理形成最终的强多分类器。实验结果表明，该方案是有效的态势要素获取方法并且精确度达到95.53%，明显优于文中其他算法，有较好的泛化能力。(As the basis of the whole network security situation awareness, the quality of situation elements extraction will directly affect the performance of the situation awareness system. To solve the problem that the situation element is difficult to extract, we propose a method to extract the hierarchical frame situation elements based on the enhanced probabilistic neural network. In the hierarchical access frame, we use the principal component analysis (PCA) to reduct the training sample attribute and to process the special attribute encoding fusion. The result can be used to optimize the structure of the probabilistic neural network (PNN) and reduce the system complexity. Take PNN as the base classifier to form the final strong classifier by repeated iteration, weight replacement and weighted fusion. The experimental results show that the scheme is an effective method to obtain the situation factors and its accuracy is 95.53%,which is significantly better than other algorithms.) Platform: |
Size: 1213440 |
Author:莫言婷婷
|
Hits:
Description: 为了真实有效地提取网络安全态势要素信息，提出了一种基于增强型概率神经网络的层次化框架态势要素获取方法。在该层次化态势要素获取框架中，根据Agent节点功能的不同，划分为不同的层次。利用主成分分析(Principal Component Analysis, PCA)对训练样本属性进行约简并对特殊属性编码融合处理，按照处理结果改进概率神经网络(Probabilistic Neural Network, PNN)结构，以降低系统复杂度。然后以改进的PNN作为基分类器，结合自适应增强算法，通过基分类器反复迭代、样本权重更新，最后加权融合处理形成最终的强多分类器。实验结果表明，本文模型较文中其他几种方法具有较高的获取准确率和良好的泛化能力。(Firstly, in order to extract the information of network security situation accurately and effectively, a hierarchical frame feature acquisition method based on enhanced probabilistic neural network is proposed. According to different functions of Agent node, the hierarchical feature acquisition framework is divided into different levels. The principal component analysis (PCA) is used to reduce the training sample attributes and the special attribute encoding fusion. The result can be used to optimize the structure of the probabilistic neural network (PNN) so as to reduce the system complexity. Then, the improved PNN is used as the base classifier. Combined with the adaptive enhancement algorithm, the final strong classifier is formed through repeated iteration, weight replacement and weighted fusion. The experimental results show that the proposed model achieve higher accuracy and better generalization ability than other methods.) Platform: |
Size: 98304 |
Author:莫言婷婷
|
Hits:
Search - probabilistic pca