Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

That's ridiculous, sorry. If that were so, we wouldn't have positional encodings in vision transformers.


It's not ridiculous if you understand how neural networks actually work. Your perception of the numbers has nothing to do w/ the logic of the arithmetic in the network.


Do you know what "positional encoding" means?


Completely irrelevant to the point being made.




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

Search: