Attention Is All You Need (Paper)

5 selectedDifficulty 5-65 unseenView topic

IntermediateNew

0 answered

5 intermediateAdapts to your performance

Question 1 of 5

120sintermediate (5/10)state theorem

Vaswani et al. (2017) introduced the Transformer with scaled dot-product attention. What does the scaling factor 1/ d_{k} correct for, and why is the scaling necessary?