← Back to Library

Learn Math for AI

Develop the linear algebra and probability depth to genuinely understand what AI systems do, where they fail, and how to think through approaches — grounded in the actual mathematics rather than marketing or vibes. The full transformer architecture, from vectors to attention.

Pillar 1 — Linear Algebra

  1. 0000 The Transformer — Your North Star overview
  2. 0001 Vectors as AI Atoms
  3. 0002 Matrices as Transformations
  4. 0003 Matrix Multiplication Engine
  5. 0004 Vector Spaces & Embeddings
  6. 0005 Projections & Residuals
  7. 0006 Eigenvalues & SVD

Pillar 2 — Probability

  1. 0007 Probability Fundamentals
  2. 0008 Conditional Probability & Bayes
  3. 0009 Random Variables & Distributions
  4. 0010 Entropy & Cross-Entropy
  5. 0011 KL Divergence

Bridge — Where the Pillars Fuse

  1. 0012 Softmax — The Bridge

The Transformer

  1. 0013 Attention Mechanism core
  2. 0014 Complete Transformer capstone

Reference

Reference materials coming soon.

Resources

Curated high-trust sources — Strang, Blitzstein, 3Blue1Brown, and the original transformer paper.
→ View Resources