AI & machine learning2022 · shared on Hacker News
Data Distributional Properties Drive Emergent Few-Shot Learning in Transformers
Explore Data Distributional Properties Drive Emergent Few-Shot Learning in Transformers, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Ysilencedogood3 ·
Data Distributional Properties Drive Emergent Few-Shot Learning in Transformers
2 points0 comments
Ybenlivengood ·
Bursty symbols in training allow prompting (ML)
2 points0 comments
Ytech-sucker ·
Data Distributional Properties Drive Emergent In-Context Learning in Transformer
1 points0 comments