litlas
ログインアカウント作成

Nonlinear Dimensionality Reduction by Locally Linear Embedding

著者: Sam T. Roweis, Lawrence K. Saul - Science 2000 被引用: 15,093

Many areas of science depend on exploratory data analysis and visualization. The need to analyze large amounts of multivariate data raises the fundamental problem of dimensionality reduction: how to discover compact representations of high-dimensional data. Here, we introduce locally linear embedding (LLE), an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs. Unlike clustering methods for local dimensionality reduction, LLE maps its inputs into a single global coordinate system of lower dimensionality, and its optimizations do not involve local minima. By exploiting the local symmetries of linear reconstructions, LLE is able to learn the global structure of nonlinear manifolds, such as those generated by images of faces or documents of text.

Nonmetric IndividualDifferences…Nonmetric Individual Differences Multidimensional Scaling: An Alternating Least Squares Method with Optimal Scaling FeaturesData structures andnetwork algorithmsData structures and network algorithmsMatrix AnalysisMatrix AnalysisTemplates for theSolution of Algebraic…Templates for the Solution of Algebraic Eigenvalue Problems: A Practical GuideSelf-Organization andAssociative Memory…Self-Organization and Associative Memory, Third EditionNonlinear principalcomponent analysis usin…Nonlinear principal component analysis using autoassociative neural networksTopology representingnetworksTopology representing networksImage Representationsfor Visual LearningImage Representations for Visual LearningDimension Reduction byLocal Principal…Dimension Reduction by Local Principal Component AnalysisGTM: The GenerativeTopographic MappingGTM: The Generative Topographic MappingLearning the parts ofobjects by non-negative…Learning the parts of objects by non-negative matrix factorizationTemplates for theSolution of Algebraic…Templates for the Solution of Algebraic Eigenvalue ProblemsNonlinear DimensionalityReduction by…Nonlinear Dimensionality Reduction by Semidefinite Programming and Kernel Matrix FactorizationGaussian ProcessDynamical Models for…Gaussian Process Dynamical Models for Human MotionData Visualization WithMultidimensional ScalingData Visualization With Multidimensional ScalingLarge Graph Constructionfor Scalable…Large Graph Construction for Scalable Semi-Supervised LearningFunctional, But NotAnatomical, Separation…Functional, But Not Anatomical, Separation of “What” and “When” in Prefrontal CortexFast ImageSuper-Resolution Based…Fast Image Super-Resolution Based on In-Place Example RegressionRobust StructuredSubspace Learning for…Robust Structured Subspace Learning for Data RepresentationPrincipal Graph andStructure Learning Base…Principal Graph and Structure Learning Based on Reversed Graph EmbeddingMolecular enhancedsampling with…Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape explorationImage Representation andLearning With…Image Representation and Learning With Graph-Laplacian Tucker Tensor DecompositionConstant Curvature GraphConvolutional NetworksConstant Curvature Graph Convolutional NetworksEnd-to-end deeprepresentation learning…End-to-end deep representation learning for time series clustering: a comparative studyNonlinear DimensionalityReduction by Locally…Nonlinear Dimensionality Reduction by Locally Linear Embedding過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。