About: The package computes the optimal parameters for the Choquet kernel

Initial Announcement on mloss.org.

About: Stochastic neighbor embedding originally aims at the reconstruction of given distance relations in a low-dimensional Euclidean space. This can be regarded as general approach to multi-dimensional scaling, but the reconstruction is based on the definition of input (and output) neighborhood probability alone. The present implementation also allows for handling dissimilarity or score-induced neighborhood topologies and makes use of quasi 2nd order gradient-based (l-)BFGS optimization.

• gradient in xsne_fun.m fixed! (constant factor m was missing)

• symmetry option re-introduced allowing for enabling symmetric and asymmetric versions of SNE and t-SNE

About: The aim is to embed a given data relationship matrix into a low-dimensional Euclidean space such that the point distances / distance ranks correlate best with the original input relationships. Input relationships may be given as (sparse) (asymmetric) distance, dissimilarity, or (negative!) score matrices. Input-output relations are modeled as low-conditioned. (Weighted) Pearson and soft Spearman rank correlation, and unweighted soft Kendall correlation are supported correlation measures for input/output object neighborhood relationships.

• Initial release (Ver 1.0): Weighted Pearson and correlation and soft Spearman rank correlation, Tue Dec 4 16:14:51 CET 2012

• Ver 1.1 Added soft Kendall correlation, Fri Mar 8 08:41:09 CET 2013

• Ver 1.2 Added reconstruction of sparse relationship matrices, Fri Jul 26 16:58:37 CEST 2013

About: The package provides a Lagrangian approach to the posterior regularization of given linear mappings. This is important in two cases, (a) when systems are under-determined and (b) when the external model for calculating the mapping is invariant to properties such as scaling. The software may be applied in cases when the external model does not provide its own regularization strategy. In addition, the package allows to rank attributes according to their distortion potential to a given linear mapping.

Version 1.1 (May 23, 2012) memory and time optimizations distderivrel.m now supports assessing the relevance of attribute pairs

Version 1.0 (Nov 9, 2011) * Initial Announcement on mloss.org.

About: Multi-class vector classification based on cost function-driven learning vector quantization , minimizing misclassification.

Initial Announcement on mloss.org.

About: Correlative Matrix Mapping (CMM) provides a supervised linear data mapping into a Euclidean subspace of given dimension. Applications include denoising, visualization, label-specific data preprocessing, and assessment of data attribute pairs relevant for the supervised mapping. Solving auto-association problems yields linear multidimensional scaling, similar to PCA, but usually with more faithful low-dimensional mappings.

Tue Jul 5 14:40:03 CEST 2011 - Bugfixes and cleanups

• single precision data affected pinv(). Now fairer using double precision.
• early stopping did not work properly; now fixed
• Hessian update mode globally controlled via hessmode, 'lbfgs' / 'bfgs'
• distmat.m corrected for rounding problems and extended to distmat(X,Y)
• replaced files: corv.m + corvgrad.m -> corvg.m
• removed unused files: corrmat.m, splitdata.m, traforankapply.m