Transformer paper

by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin · 2017

Heard in 1 episode across 1 show since Sep 2026

“Attention Is All You Need” introduced the Transformer neural-network architecture, which uses attention mechanisms rather than recurrence or convolution as its primary sequence-modeling mechanism.