What would be your advice to a 17 year old who wants to do deep learning research
I think hard problems are generally solved by simple ideas, massively scaled. But identifying these ideas is not easy -- they look and behave very different before being brought at scale
-
-
-
Do maths, learn language (python), do data structure algorithm, do MOOCs. Various moocs for deep learning and other subjects available on coursera,edx, MITOCW, udacity etc. Google also made its own site for machine learning stuff.
- Show replies
New conversation -
-
-
I would be great if you illustrated your point with an example.
-
Deep learning, computing, the universe... It's not complicated, there's just a lot of it.
- Show replies
New conversation -
-
-
Now your talking about what I call objective truth. It’s often a simple idea, but one your are willing to act out. The action is you testing the idea to see if it works well for you, and society as a whole.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
If it does, society will accept it as a viable solution to the problem at hand, if not then it’s back to the drawing board, and possibly someone else’s idea will work better
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Brute-forcing works for some problems, yes.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Like Micromobility... scooters, ebikes, etc. They look like a toy right now.
-
You beat me to it Michal!
#toysforeveryone
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.