arXiv 2012.011722020-12-01cs.CYcs.CV

ReproducedPapers.org：开放式教学和构建机器学习可重复性

ReproducedPapers.org: Openly teaching and structuring machine learning reproducibility

Delft University of Technology（代尔夫特理工大学）

Burak Yildiz, Hayley Hung, Jesse H. Krijthe, Cynthia C. S. Liem, Marco Loog, Gosia Migut, Frans Oliehoek, Annibale Panichella, Przemyslaw Pawelczak, Stjepan Pic… 展开作者

Burak Yildiz, Hayley Hung, Jesse H. Krijthe, Cynthia C. S. Liem, Marco Loog, Gosia Migut, Frans Oliehoek, Annibale Panichella, Przemyslaw Pawelczak, Stjepan Picek, Mathijs de Weerdt, Jan van Gemert

备注：: Accepted to RRPR 2020: Third Workshop on Reproducible Research in Pattern Recognition
DOI：: 10.1007/978-3-030-76423-4_1

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

我们介绍ReproducedPapers.org：一个开放的在线知识库，用于教学和构建机器学习可重复性。我们评估了在学生中进行复制项目以及人工智能研究人员在线复制库的附加值。我们使用匿名自我评估调查，并获得了144个答复。研究结果表明，学生谁做一个复制项目的地方更重视科学的复制，并成为更批判性的思想家。学生和人工智能研究人员都认为我们的在线复制库很有价值。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。