PPS, Dr Sex sounds much more scandalous than it is. Its actually Dr Sextus and I dont think he’s ever called Dr Sex in the mainstream books iirc. But Muir is the Mother of Memes so I won’t say it’s beneath her to call him that.

Holy shit. I just looked up what you’re talking about. I didnt even read those. Those are some random side stories. Start with Gideon The Ninth. Excuse me while I read Doctor Sex now :D

I’m sorry maybe you found the wrong series. I’m talking about series with the books-Gideon The Ninth, Harrow The Ninth and Nona The Ninth. Its written by Tamsyn Muir

I recommend Locked Tomb series. It has both of youre asking for. Also, such badass protagnist and overall great writing.

Universal function approximation - neural networks.

Auto-differentiation - algorithmic calculation of partial derivatives (aka gradients)

Backpropagation - when using a neural network (or most ML algorithms actually), you find the difference between model prediction and original labels. And the difference is sent back as gradients (of the loss function)

Parameter dimensionality - the “neurons” in the neural network, ie, the weight matrices.

If thats your argument, its worse than Statistics imo. Atleast statistics have solid theorems and proofs (albeit in very controlled distributions). All DL has right now is a bunch of papers published most often by large tech companies which may/may not work for the problem you’re working on.

Universal function approximation theorem is pretty dope tho. Im not saying ML isn’t interesting, some part of it is but most of it is meh. It’s fine.

deleted by creator

Bojack Horseman.

Its not the same comparison tho. Tech is a far more lucrative career than coal mining/primary ed. Inequity in tech affects a lot more than inequity in those other fields.