As someone who works in merging differential equations and machine learning, I have found this kind of work essential for what I do. Pervasive AD that allows merging neural networks and diffeq solvers is allowing us to explore all of kinds of new models and new problems. Sure it doesn't impact vanilla machine learning all that much (though Zygote.jl does allow for a lot of optimizations that wouldn't be possible with tracing-based AD), but it definitely opens up a new wave of AI possibilities.
I’m finding the ML work being done in Julia very refreshing. It feels like they are building things right from the ground up and the community is great to work with.
> [...] bake for fifteen minutes and out pops a fully-featured ML stack<p>where is logging, where is model storage and versioning, where is input data processing and normalizing, where is results processing?