100% agree. https://developers.google.com/machine-learning/guides/rules-of-ml … is the best resource I have found so far that talks deeply about applied ML
The hardest thing in machine learning is to find how to productively leverage it in your product. The second hardest thing is to collect and annotate the right dataset. Building and training models is relatively straightforward by comparison
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
The hardest thing is finding a leadership team to work for that has some sensible notion of what they want to achieve and can achieve.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
played the YouTube video outloud so had to explain to my partner; what in the world... As I attempted to, she works on clinical studies, I came to realize this parallels medicine, where gathering patients and data and coming up with an intervention overwhelmes model development
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Est ce que vous avez de bons exemples de mise en oeuvre ? (À visée pédagogique?)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Without sounding like tooooo much of a suckup: the hardest thing in deep learning (and ML by entailment) was waiting for
#Keras to be made and then integrated into#TensorFlow. All of these frameworks were a mess before that, coming from my position starting to care around 2014.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Do you mean generalizability? Anyway, reproducibility is also the issue. ML needs a class of tidy set, e.g. ExpressionSet, to compile everything such that end-to-end processing is identifiable.
End of conversation
-
-
-
@kulkajinkya remember we talked about this exact order of importanceThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
I'm using keras in python3 what are you on about?
End of 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.