threw4234324

Well, why though ? Julia has plenty of numerical libraries going for it, and all of them can be used in a differentiable manner (see, Neural ODE etc.). While Julia was built by a mix of people doing Numerical Linear Algebra and PLs (MIT, UCSD..), Swift seems to be entirely the output of the latter group.

Does anyone here use Swift for Deep Learning work ? I'm yet to see any real advantage, and even if there were or were to be added, I think Julia would almost always be a better choice here.

I know right ? Slack is horrible for archiving (and the bloat, OMG the bloat); Wave being more integrated could've had an advantage here.

The reference to Japan also brought up memories of Sony's brilliant play in the (admittedly declining) Camera market - starting off as a joke, then acquiring Minolta (not exactly a prestigious brand) and now being bigger than Canon and Nikon. In contrast, Pentax, which once ruled the Camera market (not to speak of Kodak..), is not even acknowledged by Ricoh today.

Tony Northrup's vlog on this is very interesting.

https://www.youtube.com/watch?v=KVW18cGdfUU