--------=====--------------------------------------------------------------
---------- bGURLS - (big) Grand Unified Regularized Least Squares ---------
---------------------------------------------------------------------------


Table of Contents
=================

- Introduction
- Installation
- Documentation

Introduction
===========

bGURLS - ((big) Grand Unified Regularized Least Squares) is a MATLAB software package
for training linear multiclass classifiers based on the Regularized Least Squares
(RLS) loss function, it uses a home brewed memory mapped file system and a simple
distributed task manager to allow for training from very large datasets.

Installation
============

Open MATLAB and execute:

>> run('PACKAGEROOT/biggurls/utils/biggurls_install.m');

where PACKAGEROOT is where you unzipped the GURLS package.
This will compile all the mex files involved and add all the important
directories to your path. Run 'savepath' if you want the installation to be
permanent.

Documentation
=============

- A User manual with several examples can be found here:
   https://github.com/CBCL/GURLS/wiki/3-User-Manual#wiki-GURLS_Usage

- Demos
  bGURLS has exstensively commented demos in the "demo" subdirectory. 
  Have a look, and run gurlsdemo.m. We feel this is the best way to learn how to use these packages.
	
- Description of the available methods, demos and data for each package can be found at
	https://github.com/CBCL/GURLS/wiki/4-Code-Description#wiki-bGURLS