Publication
Pattern Recognition Engineering
Faisal Shafait; Matthias Reif; Christian Kofler; Thomas Breuel
In: RapidMiner Community Meeting and Conference. RapidMiner Community Meeting and Conference (RCOMM-10), September 13-16, Dortmund, Germany, Online, 9/2010.
Abstract
This paper outlines some key software components
developed in the Pattern Recognition Engineering (PaREn)
project. The goal of the PaREn project was to create the
methods and tools necessary allowing non-experts to use, train,
test, and deploy pattern recognition and machine learning
modules in real-world software systems. A major effort in the
PaREn project was therefore automating parameter optimization, model selection, machine learning system construction,
and supporting rapid testing, validation, and on-line adaptivity.
To deliver our technologies as open source, we chose RapidMiner as the software platform. Therefore, major software
components developed in PaREn are provided as RapidMiner
extensions. The expected benefits are a far wider usage of
pattern recognition and machine learning methods, leading to
both better quality of the decisions and behaviors of software
systems, as well as lower development costs.