[Least Squares Support Vector Machines Toolbox]

Download LS-SVMlab1.5

The source code is compiled and preprared in multiple formats. To get the proper installation on your computer, follow these steps:

Depending on your interest you can either get familiar with the basic algorithms or use a more advanced toolbox by downloading the appropriate version.
- Matlab 6+: LS-SVMlab1.5 - Linux:
  
  Basic Advanced C source code
- Matlab 6+: LS-SVMlab1.5 - Windows:
  
  Basic Advanced C source code
- Matlab 5 (or older): LS-SVMlab1.5
  
  LS-SVMlab is tested on older versions of Matlab as well. A few routines call Matlab's optimization toolbox (including bay_optimize.m and bay_rr.m) and will give an error message when running LS-SVMlab under Matlab 5.
Run the following installation script. It will unpack the compressed toolbox and check the programs. Use save link as... (menu of the right mouse button) to save this file properly. The file should be saved in the same directory as the compressed toolbox. Choose according to your operating system:
- Linux: [install_linux.m]
- Windows: [install_windows.m]

	The LS-SVMlab software is made available for non commercial research purposes only under the GNU General Public License. However, notwithstanding any provision of the GNU General Public License, LS-SVMlab software may not be used for commercial purposes without explicit written permission after contacting LS-SVMlab@esat.kuleuven.be.

When reporting results obtained by LS-SVMlab, one should consider referring to

J.A.K. Suykens, T. Van Gestel, J. De Brabanter, B. De Moor, J. Vandewalle,
Least Squares Support Vector Machines,
World Scientific, Singapore, 2002 (ISBN 981-238-151-1)

LS-SVMlab 1.5 Toolbox User's Guide

An extended tutorial containing the help to all function call's is available freely:

(in Acrobat's Portable Document Format)

Introductory LS-SVMlab 1.5 paper and presentation

An introductory paper explaining the features of the toolbox is:

Pelckmans K., Suykens J.A.K., Van Gestel T., De Brabanter J., Lukas L., Hamers B., De Moor B., Vandewalle J.,
``LS-SVMlab : a Matlab/C toolbox for Least Squares Support Vector Machines,''
Internal Report 02-44, ESAT-SISTA, K.U.Leuven (Leuven, Belgium), (presented at NIPS2002 Vancouver in the demo track), 2002

(in Acrobat's Portable Document Format)

Links to related software

Mathtools
An internet resource for scientific software can be found here. Toolboxes and extensions are available for different languages including MATLAB, C/C++, FORTRAN.