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

Science Memes

10694 readers
3374 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
[email protected]
[email protected]
[email protected]
858
answer = sum(n) / len(n) (lemmy.eco.br)
submitted 3 months ago by [email protected] to c/[email protected]
129 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] -1 points 3 months ago (2 children)

I think saying machine learning is just statistics is a bit misleading. There’s not much statistics going on in deep learning. It’s mostly just “eh, this seems to work I dunno let’s keep doing it and see what happens”.

[–] [email protected] 16 points 3 months ago (1 children)

It’s mostly just “eh, this seems to work I dunno let’s keep doing it and see what happens”.

Yeah, no.

[–] [email protected] -2 points 3 months ago (1 children)

Well, eventually the thing you’re working on falls out of fashion in place for the next trendy thing.

[–] [email protected] 4 points 3 months ago

While I don't disagree with that statement at all, I honestly have no idea how it's related to my comment (probably because I'm an idjit)

[–] [email protected] 4 points 3 months ago (1 children)

But... you have to create criteria for what qualifies as success vs failure, and it's a scale, not a boolean true/false. That's where the statistics come in, especially if you have multiple criteria with different weights etc.

[–] [email protected] 3 points 3 months ago

The criteria is a loss function, which can be whatever works best for the situation. Some might have statistical interpretations, but it’s not really a necessity. For Boolean true/false there are many to choose from. Hinge loss and logistic loss are two common ones. The former is the basis for support vector machines.

But the choice of loss is just one small part in the design of a deep learning model. Choice of activation functions, layer connectivity, regularization and optimizer must also be considered. Not all of these have statistical interpretations. Like, what is the statistical interpretation between the choice of Relu and Leaky Relu? People seemed to prefer one over the other because that’s what worked best for them.