AI Lesson & Submodule

Why Self-Attention Was Needed

Compare recurrent constraints against parallel attention calculations.

Why This Matters

RNNs process tokens one-by-one, which blocks parallel GPU training and degrades long-context memory.

What You Will Learn

  • Explain sequential bottlenecks
  • Describe recurrence limits
  • Introduce attention idea

Concepts Covered

Sequential bottlenecksVanishing recurrent gradientsParallel attention scaling

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
In Progress

Technical Interview Value

  • ?Explain the fundamental training limitations of RNNs/LSTMs that led to the attention mechanism