HackerTube / Video
CS480/680 Lecture 19: Attention and Transformer Networks
Pascal Poupart
A university lecture from CS480/680 by Pascal Poupart on attention mechanisms and transformer networks, worked through on a chalkboard.
HN recommends it to newcomers as a clear explanation of attention, including the query/key/value intuition.
4 Hacker News mentions · 2023–2023