Attention Is All You Need

814,872 views

About this video

Hand-picked by a BrighterTube curator · found via HackerTube (Karpathy's dataset of videos Hacker News recommends · 85% confidence

Yannic Kilcher reads the Transformer paper line by line, explaining scaled dot-product and multi-head attention, positional encoding and the encoder-decoder diagram; a careful walkthrough of the most influential recent ML paper.

Yannic Kilcher walks through 'Attention Is All You Need' and the transformer architecture.

Video by Yannic Kilcher, played through YouTube's embedded player.

Part of Natural Language Processing, Deep Learning Architectures