A community-based platform for machine learning experimentation

Abstract

We demonstrate the practical uses of a community-based platform for the sharing and in-depth investigation of the thousands of machine learning experiments executed every day. It is aimed at researchers and practitioners of data mining techniques, and is publicly available at http://expdb.cs.kuleuven. be. The system offers standards and API's for sharing experimental results, extensive querying capabilities of the gathered results and allows easy integration in existing data mining toolboxes. We believe such a system may speed up scientific discovery and enhance the scientific rigor of machine learning research. © 2009 Springer Berlin Heidelberg.