Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Attention Mechanism
/
Softmax Saturation
Softmax Saturation
Subtopic
2 questions
Questions tagged with Softmax Saturation — part of Attention Mechanism.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Why does normalizing Q and K before the dot product help training at scale?
Short Answer
Medium
·
Qual 4.0
What specifically goes wrong if you remove the √d_k scaling from attention?
Multiple Choice
Medium
·
Qual 4.0