Deep Learning / 16
Attention
Explore queries, keys, values, attention scores, masks, and multi-head attention.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
Subtopics
- 16.01
Why Attention?
Planned guide: Why Attention. Focus on intuition, assumptions, and a worked example.
- 16.02
Attention Intuition
Planned guide: Attention Intuition. Focus on intuition, assumptions, and a worked example.
- 16.03
Query
Planned guide: Query. Focus on intuition, assumptions, and a worked example.
- 16.04
Key
Planned guide: Key. Focus on intuition, assumptions, and a worked example.
- 16.05
Value
Planned guide: Value. Focus on intuition, assumptions, and a worked example.
- 16.06
Attention Scores
Planned guide: Attention Scores. Focus on intuition, assumptions, and a worked example.
- 16.07
Scaled Dot-Product Attention
Planned guide: Scaled Dot-Product Attention. Focus on intuition, assumptions, and a worked example.
- 16.08
Softmax in Attention
Planned guide: Softmax in Attention. Focus on intuition, assumptions, and a worked example.
- 16.09
Self-Attention
Planned guide: Self-Attention. Focus on intuition, assumptions, and a worked example.
- 16.10
Cross-Attention
Planned guide: Cross-Attention. Focus on intuition, assumptions, and a worked example.
- 16.11
Causal Attention
Planned guide: Causal Attention. Focus on intuition, assumptions, and a worked example.
- 16.12
Attention Masks
Planned guide: Attention Masks. Focus on intuition, assumptions, and a worked example.
- 16.13
Multi-Head Attention
Planned guide: Multi-Head Attention. Focus on intuition, assumptions, and a worked example.
- 16.14
Attention Matrix
Planned guide: Attention Matrix. Focus on intuition, assumptions, and a worked example.
- 16.15
Computational Cost
Planned guide: Computational Cost. Focus on intuition, assumptions, and a worked example.
- 16.16
Attention Limitations
Planned guide: Attention Limitations. Focus on intuition, assumptions, and a worked example.


