this post was submitted on 08 Jul 2024
825 points (96.8% liked)

Science Memes

10833 readers
2395 users here now

Welcome to c/science_memes @ Mander.xyz!

A place for majestic STEMLORD peacocking, as well as memes about the realities of working in a lab.



Rules

  1. Don't throw mud. Behave like an intellectual and remember the human.
  2. Keep it rooted (on topic).
  3. No spam.
  4. Infographics welcome, get schooled.


Research Committee

Other Mander Communities

Science and Research

Biology and Life Sciences

Physical Sciences

Humanities and Social Sciences

Practical and Applied Sciences

Memes

Miscellaneous

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] Socsa@sh.itjust.works 50 points 3 months ago (6 children)

Bayesian purist cope and seeth.

Most machine learning is closer to universal function approximation via autodifferentiation. Backpropagation just lets you create numerical models with insane parameter dimensionality.

[–] TopRamenBinLaden@sh.itjust.works 41 points 3 months ago

I like your funny words, magic man.

[–] lseif@sopuli.xyz 8 points 3 months ago (1 children)
[–] hotsox@lemmy.blahaj.zone 18 points 3 months ago* (last edited 3 months ago)

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.

[–] kibiz0r@midwest.social 7 points 3 months ago (1 children)

A monad is just a monoid in the category of endofunctors, after all.

[–] AnarchistArtificer@slrpnk.net 3 points 3 months ago (1 children)

No, no, everyone knows that a monad is like a burrito.

(Joke is referencing this: https://blog.plover.com/prog/burritos.html )

[–] Contravariant@lemmy.world 3 points 3 months ago (1 children)

So what you're saying is that if you put a burrito inside a burrito it's still a burrito?

[–] embed_me@programming.dev 2 points 3 months ago

Any practical universal function approximation will go against entropy.

[–] feedum_sneedson@lemmy.world 1 points 3 months ago

pee pee poo poo wee wee