Study is here, and it's pretty cool: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0214365 …
-
-
Show this thread
-
Basically, the researchers made a decent statistical model and then tested the predictive power against two types of machine learning The "AI" did ~slightly~ better Cue the hilarious headlinespic.twitter.com/095CkmCGKM
Show this thread -
Now look - I'm not an expert in machine learning, I don't claim to understand exactly what's happening here But a minor improvement is definitely not earth-shattering newspic.twitter.com/kAF2cPMU0n
Show this thread -
The study is great, and hopefully these techniques can be incorporated into public health planning, but the headlines are just ridiculous
Show this thread
End of conversation
New conversation -
-
-
“3.2% better? Damn, that’s TOO GOOD”
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.