Thanks Maarten! I think you asked about this a month or so ago and I said I had a paper in the works. Well, this is that paper!
New viewpoint worth reading about reproducible machine learning by @AndrewLBeam @arjunmanrai @MarzyehGhassemi. Reproducing machine learning models can be expensive (>1M$ just to rerun the algorithms) but vital before implemented in clinical practice
https://jamanetwork.com/journals/jama/fullarticle/2758612?guestAccessKey=f7a40b11-5247-4c38-bf53-00f1389925ff&utm_source=twitter&utm_medium=social_jama&utm_term=3014867549&utm_campaign=article_alert&linkId=80045473 …pic.twitter.com/tmdDRomowl
-
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Important topic indeed. Is the issue reproducibility or generalizability? If generalizability then causal inference would have to be invoked I'm assuming
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.