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

Don't most statistical techniques rely on specific structure in the spaces containing the objects they operate on, in order to be useful?


Embeddings have structure, or they wouldn't be very useful. E.g. cosine similarity works because (many) embeddings are designed to support it.


Oh, that should have been obvious. Thank you for explaining.




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

Search: