Positional Encoding

The signal added to token embeddings so the model knows where each token sits in the sequence, since self-attention has no built-in notion of order.

Deep Learning

BACKLOG · WORK IN PROGRESS

This term is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.

Back to wiki Track progress on GitHub