Hacker News new | past | comments | ask | show | jobs | submit login

Transformers managed to confuse me about what interpolation and extrapolation really mean in high dimensional space



There's a neat argument against these models doing interpolation: the manifold of the data is so sparse that it's infinitesimally unlikely for a good predictor to be doing interpolation between existing points on the manifold.

https://arxiv.org/abs/2110.09485


Yes, nice, I know some of these words


Maybe what transformers actually transform are us..


Autobots, print out.




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

Search: