Back to Module 1.9: Self-AttentionIn Progress
AI Lesson & Submodule
Query, Key and Value
Deconstruct the role of projection matrices in generating Q, K, and V.
Why This Matters
Q, K, and V map inputs into separate spaces, allowing models to query context patterns mathematically.
What You Will Learn
- •Explain QKV projections
- •Verify vector shapes
- •Define projection weights
Concepts Covered
QKV linear projectionsWeights matrices shapesLinear mapping transforms
Mapped Foundation Project: Mini Attention Notebook
Self-contained interactive workbook computing step-by-step scaled dot-product attention scores from raw matrices input.
Architecture Preview
Dynamic math workbook running forward projections, scaling matrix outputs, and plotting soft heatmaps.
Character Tokens ArrayQKV Projections WeightsQK Dot Product Score
Tech Stack Planned
ReactTypeScriptMath.js
Technical Interview Value
- ?Explain the physical analogy of Query, Key, and Value vectors using database terminology