I was right, it is (fedia.io)

submitted 2 days ago by Lukstru@fedia.io to c/science_memes@mander.xyz

7 comments fedilink hide all child comments

Watched Primer's new video (https://www.youtube.com/watch?v=GkiITbgu0V0 watch it!) and stumbled over this gem

top 7 comments

sorted by: hot top controversial new old

[-] AtariDump@lemmy.world 4 points 1 day ago

[-] Septimaeus@infosec.pub 5 points 2 days ago* (last edited 2 days ago)

~~Gradient descent?~~ It’s loss.

[-] abbadon420@sh.itjust.works 10 points 2 days ago

Took me 17 minutes to get the joke. Good video though.

[-] UnRelatedBurner@sh.itjust.works 3 points 1 day ago

can I get my instant gratification please?

[-] abbadon420@sh.itjust.works 5 points 1 day ago* (last edited 1 day ago)

Sure, here's a TLDW.
Imagine you're training an AI model. You feed it data and test if it comes up with a good answer. Of course it doesn't do that right away, thats why you.re training it. You have to correct it.

If you correct the model by correcting the errors, you get overcompensation problems. If you correct it on the differences between the errors, you get a much better correction.

The term for that is LOSS. You correct on LOSS in stead of on pure ERROR.