I was right, it is
Submitted 4 days ago by Lukstru@fedia.io to science_memes@mander.xyz
https://fedia.io/media/1e/ea/1eeab4d3b120f66f5919bef11694b0f7e26e5ca37287f8d372f86fc583916f9b.jpg
Comments
AtariDump@lemmy.world 3 days ago
sniggleboots@europe.pub 4 days ago
I watched that video mere hours ago!
Septimaeus@infosec.pub 4 days ago
Gradient descent?
abbadon420@sh.itjust.works 4 days ago
Took me 17 minutes to get the joke. Good video though.
UnRelatedBurner@sh.itjust.works 3 days ago
can I get my instant gratification please?
abbadon420@sh.itjust.works 3 days ago
Sure, 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.