Skip to content
ml-recall

#bilinear-attention

1 question from Attention & Transformers

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

easyAI-checkedAttention & Transformers

Queries are 20-dimensional and keys 2-dimensional. Instead of additive attention you score them with the bilinear form a(q,k)=q⊤Mka(\mathbf{q}, \mathbf{k}) = \mathbf{q}^\top\mathbf{M}\mathbf{k}. How many learnable entries does M\mathbf{M} have?

a whole number