Fits my prior that most supposed ML successes would have worked even better with simpler, more reliable methods.https://twitter.com/robinhanson/status/803302419249725440 …
true… on the other hand, linear regression has been around for a while :-) Not that it’s usually adequate, but >
-
-
> there are many tools in the box, and my impulse usually would be to try the best-characterized ones first.
-
NN hype bugs me for many reasons; one is tendency to omit control experiment of trying something simpler first.
- 2 more replies
New conversation -
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.