this post was submitted on 05 Mar 2024
368 points (89.8% liked)

Science Memes

10799 readers
2067 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]
368
Maybe I am insane. Maybe it's just Maybelline. (mander.xyz)
submitted 7 months ago by [email protected] to c/[email protected]
22 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 85 points 7 months ago (3 children)

Isn't machine learning doing slightly different thing each time?

[–] [email protected] 53 points 7 months ago (1 children)

Yeah this is a bad meme. The whole point of machine learning is to do minutely different things over millions of generations to see differences and their effects. It's the exact opposite of doing the same thing and expecting different results. Machine learning is the summation of millions of differences.

[–] [email protected] 1 points 7 months ago (1 children)

I think the point is that it's the same (type of) computation or process over and over.

[–] [email protected] 1 points 7 months ago

That doesn't really work. For example, driving is the same action. I do this action over and over again. However, I drive to vastly different destinations. I'm not in fact doing the same thing over and over even though the same action is being done.

Similarly an algorithm will give vastly different results based on the inputs I give it. Saying it's the same formula with different inputs would be very incorrect.

[–] [email protected] 32 points 7 months ago (1 children)

Listen, I identify with generation 1 here.

[–] [email protected] 7 points 7 months ago

20 is how I end up

[–] captain_aggravated 7 points 7 months ago

Or do the same thing in a very slightly different way each time until you accidentally discover a good enough way to do it?