1741

Can you think of any now? (piefed.cdn.blahaj.zone)

submitted 1 week ago by LadyButterfly@piefed.blahaj.zone to c/science_memes@mander.xyz

387 comments fedilink hide all child comments

(page 2) 50 comments

sorted by: hot top controversial new old

[-] degoogler@lemmy.zip 2 points 5 days ago

In an atom, the electrons orbit around the nucleus in the same manner as the planets orbit around the sun.

That's been debunked for many many decades but middle scool still teaches this model. At least I wasn't told back then how misleading and wrong that is, only in high school right before graduating the physics teacher emphasized this misconception. I remember how mad she was about it lol. I have no clue how its taught elsewhere.

load more comments (1 replies)

[-] missfrizzle@discuss.tchncs.de 3 points 5 days ago* (last edited 5 days ago)

I was taught that serious academics favored Support Vector Machines over Neural Networks, which industry only loved because they didn't have proper education. oops...

also, Computer Vision was considered "AI-complete" and likely decades away. ImageNet dropped a couple years I graduated. though I guess it ended up being "AI-complete" in a way...

[-] bluemellophone@lemmy.world 2 points 5 days ago* (last edited 5 days ago)

Before AlexNet, SVMs were the best algorithms around. LeNet was the only comparable success case for NNs back then, and it was largely seen as exclusively limited to MNIST digits because deep networks were too hard to train. People used HOG+SVM, SIFT, SURF, ORB, older Haar / Viola-Jones features, template matching, random forests, Hough Transforms, sliding windows, deformable parts models… so many techniques that were made obsolete once the first deep networks became viable.

The problem is your schooling was correct at the time, but the march of research progress eventually saw 1) the creation of large, million-scale supervised datasets (ImageNet) and 2) larger / faster GPUs with more on-card memory.

It was fact back in ~2010 that SVMs were superior to NNs in nearly every aspect.

Source: started a PhD on computer vision in 2012

load more comments (2 replies)

[-] Kolanaki@pawb.social 5 points 6 days ago

Every subject other than English and Math have tons of things that were wrong, misunderstood, or made up back when I was in school. 😩