It would be fascinating to instrument deep learning developer workflows, so as to run the numbers on the productivity increase that comes from using tools that reduce cognitive load vs. tools that lay traps for you to fall into
Show this thread
-
The first thing that users that recently switched to Keras mention to me is the productivity boost. In the time it would have taken them to debug their way through the implementation of one idea (`zero_grad()` anyone?), they can try out 2, 3 ideas.
Show this thread
It matters because trying more ideas (with fewer mistakes) means you will converge faster towards better ideas (thus winning competitions more often or increasing your paper acceptance rate). I'm thinking Kaggle kernels or Colab would be a way to gather hard data on this...
-
-
1/ In cognitive science there is an interesting paradox. Reducing the effort to learn something often reduces the retention and understanding of a subject.
-
2/ Thus, a high-level framework can give an initial productivity boost. But once you need to add custom functionality, a low-level framework can lead to a productivity boost. Since a user has a better understanding and retention of the underlying components.
End of conversation
New conversation -
-
-
At
@AlpesAi we try to do the same Our API allows developers to try new ideas very very fast and converge on the best solutions. -
u hav mentioned in website as o(nlogn) but ur paper by eswaran says different "The computational complexity is O(n.N log(N)) + O(n3 log(N)), where N is the given number of points and n3 is the cube of n - the dimension of space."?
- Show replies
New conversation -
-
-
Performence of the framework should be dependent on type of ideas users want to iterate on(low-level, high-level, ...). Users should choose framework dependent on how much control they usually need. Having too much -> debugging hell. Too little -> lose hours with documentation.
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.