Oh you gots thy overfitthy? Where are my leeches?
I'd guess I'd summarize it as, being a "deep learning expert" in 2021 is like being a "medicine expert" in 1800. You know a lot less than you think, and most of what you think you know is wrong. Just keep learning and experimenting, and don't play stupid status games.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
They should take gpt3 and add an arithmetic and physics unit.pic.twitter.com/8V2zoBriYc
-
It should be trained on math, physics and engineering textbooks, then have the chance to self learn with videos and by controlling robots.
End of conversation
New conversation -
-
-
This Tweet is unavailable.
-
Probably. All learning processes exhibit U-shaped learning. Kids say “goed“. 2nd year med students make more misdiagnoses than correct ones. But It would have been really bad for us in 2020 if they had abandoned medicine in 1800 because at the time were at the bottom of the U.
End of conversation
-
-
-
You've earned the right to be humble, but the rest of us have to fight for our place under the sun.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Being able to write http://model.fit (x, y) is enough to be AI/ML expert on Linkedin
-
To elevate to AI spiritual leader, just pick a hyperparameter and have a random unjustified opinion. "you should use adagrad with learning rate 0.005, add another hidden layer of sqrt the size of the input layer, run it through 3 fold CV and sacrifice your children to Imhotep"
End of conversation
New conversation -
-
-
very good.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I fully agree, considering that most "AI god's" take their ego from XGBoost or DL driven Kaggle results
-
I learnt a lot from the "AI god's" which throw around XGBoost and DL. I'd say data science in the real world is easier than competing on Kaggle The "AI god's" have built a wonderful community and are willing to share their knowledge all around
End of conversation
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.