This new interface has two facets: data collection & annotation processes on one hand, and loss function engineering on the other hand -- a way to specify the abstractions you want to encode, and what you need to do with them.
Show this thread
Machine Learning is fundamentally a computing UI innovation, much like desktop GUI + mice, or spreadsheet software. A new interface between what people want, and the production of computer programs that implement it. A new medium.
-
-
-
What everyone is so focused on -- the big piles of nonlinear transforms trained with gradient descent -- is just an implementation detail in the background.
Show this thread
End of conversation
New conversation -
-
-
New?
-
This Tweet is unavailable.
- Show replies
New conversation -
-
-
Have you writtena any books on philosophy? I'd love to read them.
-
Yeah, he is more a philosopher than a scientist.
End of conversation
New conversation -
-
-
If you were going to use machine learning with Googles Ad API, what recommendations would you make? I've written numerous scripts to manage campaigns, but want to explore ML implementations. Ty
-
Can you share more on this? Examples too
End of conversation
New conversation -
-
-
Isn't this true for anything useful? Are databases a computing UI innovation? They are interfaces between people who want to retrieve data and data management system.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Ty so insightful
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.