We present ReproducedPapers.org: an open online repository for teaching and structuring machine learning reproducibility. We evaluate doing a reproduction project among students and the added value of an online reproduction repository among AI researchers. We use anonymous self-assessment surveys and obtained 144 responses. Results suggest that students who do a reproduction project place more value on scientific reproductions and become more critical thinkers. Students and AI researchers agree that our online reproduction repository is valuable.
@article{arxiv.2012.01172,
title = {ReproducedPapers.org: Openly teaching and structuring machine learning reproducibility},
author = {Burak Yildiz and Hayley Hung and Jesse H. Krijthe and Cynthia C. S. Liem and Marco Loog and Gosia Migut and Frans Oliehoek and Annibale Panichella and Przemyslaw Pawelczak and Stjepan Picek and Mathijs de Weerdt and Jan van Gemert},
journal= {arXiv preprint arXiv:2012.01172},
year = {2021}
}
Comments
Accepted to RRPR 2020: Third Workshop on Reproducible Research in Pattern Recognition