All entries.
Showing Items 411-420 of 631 on page 42 of 64: First Previous 37 38 39 40 41 42 43 44 45 46 47 Next Last

About: We study the problem of robust feature extraction based on L21 regularized correntropy in both theoretical and algorithmic manner. In theoretical part, we point out that an L21-norm minimization can be justified from the viewpoint of half-quadratic (HQ) optimization, which facilitates convergence study and algorithmic development. In particular, a general formulation is accordingly proposed to unify L1-norm and L21-norm minimization within a common framework. In algorithmic part, we propose an L21 regularized correntropy algorithm to extract informative features meanwhile to remove outliers from training data. A new alternate minimization algorithm is also developed to optimize the non-convex correntropy objective. In terms of face recognition, we apply the proposed method to obtain an appearance-based model, called Sparse-Fisherfaces. Extensive experiments show that our method can select robust and sparse features, and outperforms several state-of-the-art subspace methods on largescale and open face recognition datasets.

Changes:

Initial Announcement on mloss.org.


Logo LHOTSE 0.14

by mseeger - November 26, 2007, 21:12:19 CET [ Project Homepage BibTeX ] 4653 views, 27 downloads, 0 comments, 0 subscriptions

About: *LHOTSE* is a C++ class library designed for the implementation of large, efficient scientific applications in Machine Learning and Statistics.

Changes:

Initial Announcement on mloss.org.


Logo r-cran-bigRR 1.3-10

by r-cran-robot - August 23, 2014, 00:00:00 CET [ Project Homepage BibTeX Download ] 4640 views, 1170 downloads, 0 subscriptions

About: Generalized Ridge Regression (with special advantage for p >> n cases)

Changes:

Fetched by r-cran-robot on 2017-01-01 00:00:03.551573


Logo r-cran-grpreg 2.3-0

by r-cran-robot - February 10, 2013, 00:00:00 CET [ Project Homepage BibTeX Download ] 4610 views, 1079 downloads, 0 subscriptions

About: Regularization paths for regression models with grouped covariates

Changes:

Fetched by r-cran-robot on 2013-04-01 00:00:05.489694


Logo Epistatic MAP Imputation 1.1

by colm - November 25, 2010, 21:01:10 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4600 views, 1049 downloads, 1 subscription

About: Epistatic miniarray profiles (E-MAPs) are a high-throughput approach capable of quantifying aggravating or alleviating genetic interactions between gene pairs. The datasets resulting from E-MAP experiments typically take the form of a symmetric pairwise matrix of interaction scores. These datasets have a significant number of missing values - up to 35% - that can reduce the effectiveness of some data analysis techniques and prevent the use of others. This project contains nearest neighbor based tools for the imputation and prediction of these missing values. The code is implemented in Python and uses a nearest neighbor based approach. Two variants are used - a simple weighted nearest neighbors, and a local least squares based regression.

Changes:

Initial Announcement on mloss.org.


Logo Hub Miner 1.1

by nenadtomasev - January 22, 2015, 16:33:51 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4599 views, 819 downloads, 2 subscriptions

About: Hubness-aware Machine Learning for High-dimensional Data

Changes:
  • BibTex support for all algorithm implementations, making all of them easy to reference (via algref package).

  • Two more hubness-aware approaches (meta-metric-learning and feature construction)

  • An implementation of Hit-Miss networks for analysis.

  • Several minor bug fixes.

  • The following instance selection methods were added: HMScore, Carving, Iterative Case Filtering, ENRBF.

  • The following clustering quality indexes were added: Folkes-Mallows, Calinski-Harabasz, PBM, G+, Tau, Point-Biserial, Hubert's statistic, McClain-Rao, C-root-k.

  • Some more experimental scripts have been included.

  • Extensions in the estimation of hubness risk.

  • Alias and weighted reservoir methods for weight-proportional random selection.


Logo JMLR BudgetedSVM v1.1

by nemanja - February 12, 2014, 20:53:45 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4583 views, 842 downloads, 1 subscription

About: BudgetedSVM is an open-source C++ toolbox for scalable non-linear classification. The toolbox can be seen as a missing link between LibLinear and LibSVM, combining the efficiency of linear with the accuracy of kernel SVM. We provide an Application Programming Interface for efficient training and testing of non-linear classifiers, supported by data structures designed for handling data which cannot fit in memory. We also provide command-line and Matlab interfaces, providing users with an efficient, easy-to-use tool for large-scale non-linear classification.

Changes:

Changed license from LGPL v3 to Modified BSD.


About: You should never compute, maintain, or update the inverse of a symmetric positive definite matrix if you do not have to. Computing the inverse or manipulating it is inherently instable. You can [...]

Changes:

Initial Announcement on mloss.org.


Logo pboost 1.0

by nowozin - November 13, 2007, 08:48:28 CET [ Project Homepage BibTeX Download ] 4534 views, 1157 downloads, 0 subscriptions

About: The pboost toolbox is a set of command line programs and a Matlab wrapper for mining frequent subsequences and sequence classification. For our purposes, a sequence is defined an ordered sequence of [...]

Changes:

Initial Announcement on mloss.org.


Logo r-cran-penalizedSVM 1.1

by r-cran-robot - August 2, 2010, 00:00:00 CET [ Project Homepage BibTeX Download ] 4523 views, 949 downloads, 0 subscriptions

About: Feature Selection SVM using penalty functions

Changes:

Fetched by r-cran-robot on 2013-04-01 00:00:07.509844


Showing Items 411-420 of 631 on page 42 of 64: First Previous 37 38 39 40 41 42 43 44 45 46 47 Next Last