>> I'm getting kind of sick of this "deep learning is a black box" trope, because it's really not true anymore.

I know, right? Like, take this model I trained this morning. Here's the parameters it learned:

[0.230948, 0.00000000014134, 0.1039402934, 0.000023001323, 0.00000000000005]

I mean, what's "black-box" about that, really? You can instantly:

(a) See exactly what the model is a representation of.

(b) Figure out what data was used to train it.

(c) Understand the connection between the training data and the learned model.

It's not like the model has reduced a bunch of unfathomably complex numbers to another, equally unfathomable. You can tell exactly what it's doing- and, with some visualisation, it gets even better.

Because then it's a curve. Everyone groks curves, right?

Right, you guys?

/s obviously.