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

Thanks! Mostly Keynote, and lots of iteration.

I'll be honest, I personally found this figure puzzling. Still not 100% clear on it, but I don't believe it refers to the negative sampling approach. My best guess is that it's referring to earlier word2vec variants where the input in skipgram (or sum of inputs in CBOW) are multiplied by a weights matrix that projects the input to an output vector.

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