LIBOL

 

A Library for Online Learning Algorithms

Overview

LIBOL is an open-source library that consists of a large family of state-of-the-art online learning algorithms for machine learning and data mining research. Currently it supports 16 different online linear algorithms and variants for binary classificaiton and 13 different linear algorithms and variants for multiclass classification. <more...>

 

News

The new release (Version 0.3.0) can be downloaded from here.

 

23/12/2013

Our software was accpeted by JMLR Machine Learning Open Source Software (MLOSS).

 

12/12/2013

The new beta version (version 0.3.0) is now availabe! A template for new algorithms has been created to facilitate the implementation of new algorithms; more comprehensive documentation has been updated.

 

23/09/2013
The new beta version (version 0.2.3) is now availabe! It has been made fully compatibly with the Octave environement across multiple platforms.

 

27/07/2013
The new beta version (version 0.2.0) is now availabe! It includes both MATLAB and C implementations, and support both binary and multiclass classification.

 

04/05/2013
Dr Hoi gave the tutorial for "Online Learning for Big Data Mining" at SDM2013. The slides are now available online!

 

27/12/2012
The MATLAB beta version (version 0.1.0) is now availabe!

 

6/7/2012
The MATLAB alpha version is now availabe for testing upon email request. The beta version will be released very soon!



Navigation