You are reading immutable version 40. The current guide may be newer.

Study the paper

Attention Is All You Need

Lessons, visuals, quizzes, flashcards, and resources—organized in teaching order.

All activities

Comparing Self-Attention, Recurrent, and Convolutional Layers

Comparing Self-Attention, Recurrent, and Convolutional Layers

Card 1 of 3

What is the per-layer computational complexity for Self-Attention, Recurrent, and Convolutional layers?