Principal Manifold Learning by Sparse Grids

The construction of lower-dimensional manifolds from high-dimensional data is an important task in data mining, machine learning and statistics. The authors consider principal manifolds as a regularized, non-linear empirical quantization error functional.

Подобные документы

  • Multidimensional data distributions with complex topologies and variable local dimensions. A new type of low-dimensional "principal object": a principal cubic complex. The method of topological grammars with the minimization of an elastic energy.

    статья, добавлен 08.02.2013

  • Analyzing multi-dimensional data with complex geometry and to identify low-dimensional "principal objects" that relate to the optimal projection while losing the least amount of information. The methods for dimensionality reduction of microarray data.

    статья, добавлен 08.02.2013

  • The algorithm of the basic components of a linear analysis. Work on nonlinear PCA, or NLPCA, autoassociative's neural networks, principal curves and manifolds, kernel the combination's of these approaches. The problem areas that require research.

    статья, добавлен 08.02.2013

  • Auto-associative models as a new tool for building nonlinear principal component analysis methods. The successive approximations of a dataset by manifolds of increasing dimensions. The theoretical comparison between PCA and auto-associative models.

    статья, добавлен 08.02.2013

  • Linear Principal Components. A linear model formulation. The Principal Curve and Surface models. Theory for principal curves and surfaces. Algorithmic details. Estimation of curves and surfaces. Gold assay pairs. Generalized linear principal components.

    дипломная работа, добавлен 08.02.2013

  • Spatial relationships and examples of three-dimensional figures. The calculation of the surface area of three-dimensional figures and volume of cylinders and prisms. The ratio of the volume of the cone and the pyramid to the volume of cylinder and prism.

    презентация, добавлен 10.11.2015

  • Determining the extent of interpolated approximation spaces generated by regular elliptic operators on compact manifolds. Features and through the application of Jackson-Bernstein inequalities for spectral approximation regular elliptic operators.

    статья, добавлен 25.03.2016

  • The unsupervised methods required to reduce the dimension of the data set and to extract meaningful biological information. This work shows that Independent Component Analysis is a promising approach for the analysis of genome-wide transcriptomic data.

    статья, добавлен 08.02.2013

  • Subject and method of statistical science. Elements of probability theory. Random variables and their distribution laws. Fundamental of statistical observation. Grouping, consolidated return and data presentation. Basics of averages statistics method.

    учебное пособие, добавлен 24.12.2013

  • Characterization of symmetric linear functionals as the simplest polynomials. The proof of the theory that every symmetric continuous linear functional on the complex space L (0,1) can be represented as the Lebesgue integral, multiplied by a constant.

    статья, добавлен 25.03.2016

Работы в архивах красиво оформлены согласно требованиям ВУЗов и содержат рисунки, диаграммы, формулы и т.д.
PPT, PPTX и PDF-файлы представлены только в архивах.
Рекомендуем скачать работу и оценить ее, кликнув по соответствующей звездочке.