Federated learning?
I am pretty critical of deep learning in general. Simultaneously, I invest tons of work into deep learning. I don't intend to dwell on its limitations and leave it at that. I want to overcome them. I *am* a deep learning fan.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is pretty deep.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You are deeply entrenched into this mess.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Because its something which gets things done, but we are almost as clueless abt why and how it is working in the first place. Is that why ?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Are you simultaneously an AGI fan? You seem to be pretty critical of John McCarthy's ideas, I thought I might just ask.
- Show replies
New conversation -
-
-
Instead of spending all of your time building f(x) approximators, why don't you solve cancer, healthcare, da digital divide, da wealth divide, da education divide, & other
#SocialMobility problems by a solution that scales & creates a change rather than another expert system. 42 -
New conversation -
-
-
Don't worry, we are still in love with your Xception ... But really when are you going to add mobilenet v3, EfficientNet and shuffleNet to the keras Please never ever let pytorch become more popular....
-
Pfft, efficientnet is old news
MixNet is the new thing 
- 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.