I was right, it is : science_memes@mander.xyz

I was right, it is (fedia.io)

submitted 1 year 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

all 7 comments

sorted by: hot top controversial new old

[–] abbadon420@sh.itjust.works 10 points 1 year ago (3 children)

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

hideshow 3 child comments

[–] UnRelatedBurner@sh.itjust.works 3 points 1 year ago (2 children)

can I get my instant gratification please?

parent

hideshow 2 child comments

[–] abbadon420@sh.itjust.works 6 points 1 year ago* (1 child)

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.

parent

hideshow 1 child comment

[–] UnRelatedBurner@sh.itjust.works 2 points 1 year ago

haha, loss

parent

[–] sniggleboots@europe.pub 6 points 1 year ago

I watched that video mere hours ago!

[–] Septimaeus@infosec.pub 5 points 1 year ago* (last edited 1 year ago)

~~Gradient descent?~~ It’s loss.

[–] AtariDump@lemmy.world 4 points 1 year ago