Hacker News new | ask | show | jobs
Spaced repetition is more than memorization – it's also generalization (justinmath.com)
34 points by JustinSkycak 633 days ago
2 comments

I'm assuming this article is meant for the general public and not people in specific industry but I don't know what generalization means in this context and this article does a piss poor job of explaining it. Constantly repeating "generalization of learning" doesn't get me any closer to understanding.
Generalization is standard lingo in machine learning – it's about going from known data (training set / test set) to new data which shares the same underlying patterns but wasn't available at learning time.

Taking the posts simple polynomial example, it would be going from

4x^2 + 2x -3 = 0

to

2x^2 -5x +2 = 0

or more generally to

ax^2 + bx + c = 0

The intended audience is people who are knowledgeable about spaced repetition, and such people typically know what generalization means in the context of learning.
I mean, just the standard dictionary meaning of generalization works just fine here, no? I had no problems following the article.
Could this work for training AI? Has anyone tried?
It's been tried and seemingly works well!

https://arxiv.org/abs/2409.06131