Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Making Transformers Do Math (vatsadev.github.io)
1 point by jxmorris12 on Dec 9, 2024 | past
Whats better: Neural nets wider with less layers or thinner with more layers (vatsadev.github.io)
32 points by vatsadev on June 27, 2024 | past | 7 comments
Transformers learn patterns, math is patterns (vatsadev.github.io)
2 points by senseiV on March 23, 2024 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: