Technology

59378 readers

2704 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

[email protected]

-31

A.I. groks 66%-76% faster with data augmentation strategies. (arxiv.org)

submitted 2 months ago by [email protected] to c/[email protected]

22 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[+] [email protected] -7 points 2 months ago (6 children)

We follow the classic experimental paradigm reported in Power et al. (2022) for analyzing “grokking”, a poorly understood phenomenon in which validation accuracy dramatically improves long after the train loss saturates. Unlike the previous templates, this one is more amenable to open-ended empirical analysis (e.g. what conditions grokking occurs) rather than just trying to improve performance metrics

[–] [email protected] 4 points 2 months ago (5 children)

Oh okay so they're just redefining words that are already well-defined so they can make fancy claims.

[–] [email protected] -3 points 2 months ago (4 children)

Well-defined for casual use is very different than well-defined for scholarly research. It's standard practice to take colloquial vocab and more narrowly define it for use within a scientific discipline. Sometimes different disciplines will narrowly define the same word two different ways, which makes interdisciplinary communication pretty funny.

load more comments (3 replies)