Attention Modules

Single-Headed Attention

Introduced by Merity in Single Headed Attention RNN: Stop Thinking With Your Head

Single-Headed Attention is a single-headed attention module used in the SHA-RNN language model. The principle design reasons for single-headedness were simplicity (avoiding running out of memory) and scepticism about the benefits of using multiple heads.

Source: Single Headed Attention RNN: Stop Thinking With Your Head

Papers


Paper Code Results Date Stars

Categories