From ZULU to RERS - Lessons Learned in the ZULU Challenge
Falk Maria Howar, Bernhard Steffen, Maik Merten · 2010
Abstract This paper summarizes our experience with the ZULU chal-lenge on active learning without equivalence queries, presents our win-ning solution, investigates the character of ZULU’s rating approach, and discusses how this approach can be taken further to establish a frame-work for the systematic investigation of domain-specific, scalable learning solutions for practically relevant application. In particular, it discusses the RERS initiative, which provides a community platform together with a learning framework that allows users to interactively compose complex learning solutions on the basis of libraries for various learning compo-nents, system connectors, and other auxiliary functionality. This frame-work will be the backbone for an extended challenge on learning in 2011. 1