Weka (machine learning)

From Wikipedia, the free encyclopedia

Weka is a suite of machine learning software written in Java at the University of Waikato which implements numerous machine learning algorithms from various learning paradigms.

Contents 1 Description 2 See also 3 References 4 External links 4.1 General 4.2 Weka project acquired by Pentaho 4.3 Examples of applications

[edit] Description

The focus of the algorithms implemented in Weka is on pattern classification, regression, and clustering. In addition, several further algorithms are provided, including meta-level frameworks such as ensembles. Weka is free open-source software under the GNU Public License (GPL).

Since 1993, Weka was developed at University of Waikato in New Zealand. In September 2006, the Weka project was acquired by Pentaho^[1], an open-source business intelligence software company.

[edit] See also

• YALE (Yet Another Learning Environment) Open-source machine learning framework implemented in Java fully integrating Weka.

[edit] References

1. ^ Press release: Pentaho acquires Weka

[edit] External links

[edit] General

• Weka Project home page at University of Waikato in New Zealand.
• Weka Project home page at SourceForge.net (SF.net).
• Pentaho

[edit] Weka project acquired by Pentaho

• Weka forum posting (2006/09/19)
• Pentaho Press release (2006/09/19)
• FAQ

[edit] Examples of applications

• Gene selection from microarray data for cancer classification
• QSPR of metal complexation
• Classification of Expressed sequence tag (EST) data from plant/pathogen interface