Live data from Hacker News

Viewing profile — MichaelStaniek

MichaelStaniek

HN member
Joined
Mon, Jun 03, 2019, 10:38 PM UTC
HN karma
6
Public activity
2 items

About MichaelStaniek

No profile information was provided.

Recent public activity

  1. comment
    Comment #20089815

    Yes, but thats also what happens in the normal formulation, no? So the second weight matrix actually are our context embeddings?

  2. comment
    Comment #20089726

    My intuition for that, and you can tell me if its wrong. The normal explanation for Word2Vec is 2 weight matrices, so the formula looks like this: (One_hot_input x W1) x W2, which …