Previous work has demonstrated that the image variations of many objects (human faces in particular) under variable lighting can be effectively modeled by low dimensional linear spaces. The typical linear subspace learning algorithms include Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Locality Preserving Projection (LPP). All of these methods consider an n1 × n2 ...

With the advent of high-throughput data recording methods in biology and medicine, the efficient identification of meaningful subspaces within these data sets becomes an increasingly important challenge. Classical dimension reduction techniques such as principal component analysis often do not take the large statistics of the data set into account, and thereby fail if the signal space is for ex...

The paper presents an algorithm for identifying the independent subspace analysis model based on source dynamics. We propose to separate subspaces by decoupling their dynamic models. Each subspace is extracted by minimizing the prediction error given by a first-order nonlinear autoregressive model. The learning rules are derived from a cost function and implemented in the framework of denoising...

Asymptotic analysis methods for performance prediction of so-called subspace direction-of-arrival estimation methods has been developed earlier, assuming that a large-enough number of array measurements, or snapshots, is collected. This paper also addresses the problem of making performance predictions, but for beamspace-based subspace methods. The novel approach in this paper assumes the numbe...

Subspace analysis in computer vision is a generic name to describe a general framework for comparison and classification of subspaces. A typical approach in subspace analysis is the subspace method (SM) that classify an input pattern vector into several classes based on the minimum distance or angle between the input pattern vector and each class subspace, where a class subspace corresponds to ...

 In network code setting, a constant dimension code is a set of k-dimensional subspaces of F nq . If F_q n is a nondegenerated symlectic vector space with bilinear form f, an isotropic subspace U of F n q is a subspace that for all x, y ∈ U, f(x, y) = 0. We introduce isotropic subspace codes simply as a set of isotropic subspaces and show how the isotropic property use in decoding process, then...

A new guideline for proper allocation of multipoles in the multiple multipole method (MMP) is proposed. In an ‘a posteriori’ approach, subspace fitting (SSF) is used to find the best location of multipole expansions for the two dimensional dielectric scattering problem. It is shown that the best location of multipole expansions (regarding their global approximating power) coincides with the med...

We give a general overview of the state-of-the-art in subspace system identification methods. We have restricted ourselves to the most important ideas and developments since the methods appeared in the late eighties. First, the basis of linear subspace identification are summarized. Different algorithms one finds in literature (Such as N4SID, MOESP, CVA) are discussed and put into a unifyin...

in this paper, we represent an inexact inverse subspace iteration method for com- puting a few eigenpairs of the generalized eigenvalue problem ax = bx[q. ye and p. zhang, inexact inverse subspace iteration for generalized eigenvalue problems, linear algebra and its application, 434 (2011) 1697-1715 ]. in particular, the linear convergence property of the inverse subspace iteration is preserved.