Connect your moderator Slack workspace to receive post notifications:
Sign in with Slack

Lab 13 Matrix Factorization initialization

Hi, I had a couple of questions regarding the matrix factorization initialization in lab 13. First off, why are the shapes of the item and user matrices given as (K, D) and (K, N) instead of (D, K) and (N, K) as done in the lectures? The other question I had was about the initialization that is used for the item matrix. Why is it randomly generated and then inserts the means of each item in the first row? Thanks in advance for your time :)

Page 1 of 1

Add comment

Post as Anonymous Dont send out notification