Practice free →
HomeClaudeaifoundationstransformer_attention › Multi-head attention is preferred over a single …

Multi-head attention is preferred over a single d_model-dimensional head because

AMulti-head reduces total parameter count substantially
BHeads attend to different representation subspaces
CSingle-head attention requires much more GPU memory
DSingle-head attention has higher arithmetic complexity
Answer & Solution
Correct answer: B. Heads attend to different representation subspaces
With a single head, averaging blurs information across positions. Multi-head lets the model jointly attend to different representation subspaces — distinct heads can learn distinct relations (syntax, coreference, etc.).
Solve this in the app — Claude practice & 24k+ MCQs →
Related questions