Attention Mechanisms Quiz
5 questions Pass: 70% +25 pts (50 with Pro)
Quiz covering Transformers and Attention
What you'll be asked
- What is the primary purpose of the 'Attention' mechanism in a Transformer model?
- In the context of Self-Attention, what do the Query (Q), Key (K), and Value (V) vectors represent?
- Why is 'Multi-Head Attention' preferred over a single 'Attention' head in Transformer architectures?
- What is the role of the 'Scaled Dot-Product' in the attention calculation?
- In a Transformer's decoder, why is 'Masked Multi-Head Attention' used instead of standard multi-head attention?
Answers and explanations come after you submit.
Course Content