Interesting points from yesterday's survey (note: the sample is not random, thus not representative of anything, make of it what you will):
-
Is still interesting results though, to see the other conditional preferences assuming they're already familiar w/ deep learning techniques.
The results are biased of course, but in practice DL does get far higher mindshare than shallow ML. People try it first. That's a good thing
-
-
DL may not always be the best solution, but it will usually be at least 2nd best, and clearly the best for any perception problem
-
This is strongly reflected on Kaggle, where most problems are solved with either XGBoost, Keras, or some combination of the two
- Show 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.