Zenaique
Topics
Practice
Study
Browse
Reference
Pricing
Search…
⌘K
Topics
/
Attention Mechanism
/
Sqrt Dk
Sqrt Dk
Subtopic
2 questions
Questions tagged with Sqrt Dk — part of Attention Mechanism.
Premium questions for this topic
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Why is the dot product scaled by √d_k in attention? Derive the variance argument.
Short Answer
Hard
Premium
What specifically goes wrong…
Multiple Choice
Medium
Forethought
Microsoft
Ey
Figure Ai