Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
The replicability crisis in ML and AI (technologyreview.com)
3 points by kalyanv on Nov 17, 2020 | hide | past | favorite | 1 comment



"But it is only a start. Haibe-Kains points out that code alone is often not enough to rerun an experiment. Building AI models involves making many small changes—adding parameters here, adjusting values there. Any one of these can make the difference between a model working and not working. Without metadata describing how the models are trained and tuned, the code can be useless. “The devil really is in the detail,” he says."

This is so true, many a times we try to replicate results from other papers, even if the code is available, it just simply does not work.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: