2020 Kaggle survey: regression, decision trees and ensembles dominate in ML applications.pic.twitter.com/dZTzI7wskV
-
Like arguing that a hammer is a tool used more often than a cordless drill. Tools that are cheaper to use are used more often for simpler problems.
No, different tools are better for different things, and deep learning is only best for some things.
-
-
Indeed. You can't substitute a random forest to do what a deep learning solution does best. As the saying goes, 'don't bring a knife to a gun fight'.
-
And you shouldn’t use a deep network in the many applications where other methods are best, either.
- Näytä vastaukset
Uusi keskustelu -
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.