Project details for RLS2 MATLAB Toolbox

Screenshot RLS2 MATLAB Toolbox 0.6

by posaune - February 1, 2010, 17:27:09 CET [ Project Homepage BibTeX Download ]

view (3 today), download ( 1 today ), 1 subscription


RLS2 MATLAB Toolbox is a set of scripts that implements RLS2 (regularized least squares with two layers) and RLS2LIN (linear regularized least squares with two layers).

RLS2 is an instance of multiple kernel learning algorithm that can be used to simultaneously learn a regularized predictor and the kernel function. It is also an instance of "kernel machine with two layers" that extends the classic regularized least squares algorithm.

RLS2LIN is a version of RLS2 specialized to linear kernels on each feature. RLS2LIN simultaneously performs regularization and linear feature selection, is memory efficient and well suited for datasets with a large number of features.

The package contains a Graphic User Interface (GUI) to load data, perform training and validation of RLS2 models, and plot results. The features of the toolbox include:

* Data pre-processing.
* Efficient regularization path computation.
* Cross-validation.
* Random splits.
* Hold-out set validation.
* Multi-class classification (one versus all).
* Multi-output regression.
* Approximate degrees of freedom computation.
* Plot results and export figures to PDF format.
Changes to previous version:

Supported multi-class classification (one versus all) and multi-output regression.

BibTeX Entry: Download
URL: Project Homepage
Supported Operating Systems: Platform Independent
Data Formats: Matlab
Tags: Mkl, Kernel Methods, Sparsity
Archive: download here

Other available revisons

Version Changelog Date
  • New kernel functions (rbfall, rbfsingle, polyall, polysingle)
  • Improved interface for pre-processing operations
  • The interface now allows to disable bias
  • Fixed bugs in parameter passing (thanks to Andrea Schirru)
March 31, 2010, 20:37:11

Supported multi-class classification (one versus all) and multi-output regression.

February 1, 2010, 17:27:09

Supported multi-class classification (one versus all) and multi-output regression.

January 14, 2010, 17:17:57


No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.