Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Attention Mechanism
/
Softmax Jacobian
Softmax Jacobian
Subtopic
1 questions
Questions tagged with Softmax Jacobian — part of Attention Mechanism.
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
·
Qual 4.0