Skip to content
Instant download · PDF + web edition · Free sample of every book · 30-day refund promise
Latent Library Browse books
Fundamentals

Linear Algebra for AI

Vectors, Matrices and the Geometry of Learning

Pages
80
Chapters
39
Level
Intermediate
Format
E-book

About this book

Every modern AI model is, underneath, a large amount of linear algebra. Embeddings are vectors, layers are matrices, attention is a set of dot products. This book makes that machinery intuitive.

Starting from vectors as arrows and lists of numbers, it covers dot products and similarity, matrices as transformations, matrix multiplication, systems of equations, rank, eigenvectors and the singular value decomposition, always connecting each idea to where it appears in AI. Worked examples are small enough to compute by hand.

You need school algebra and patience; no university mathematics is assumed.

What you will learn

  • Vectors, length, angle and the dot product
  • Matrices as transformations of space
  • Matrix multiplication and why layers are matrices
  • Solving systems, rank and what can be inverted
  • Eigenvectors, eigenvalues and PCA
  • The singular value decomposition and low-rank ideas

Table of contents

  1. IntroductionIntroduction
  2. Chapter 1Vectors as Lists and Arrows
  3. Chapter 2Adding and Scaling Vectors
  4. Chapter 3Length
  5. Chapter 4Unit Vectors and Normalisation
  6. Chapter 5The Dot Product
  7. Chapter 6Angles and Cosine Similarity
  8. Chapter 7Projections
  9. Chapter 8Other Norms
  10. Chapter 9Linear Combinations and Span
  11. Chapter 10Matrices as Tables of Numbers
  12. Chapter 11Matrices as Transformations
  13. Chapter 12Matrix Multiplication
  14. Chapter 13The Identity and Inverses
  15. Chapter 14Determinants
  16. Chapter 15Systems of Linear Equations
  17. Chapter 16Least Squares
  18. Chapter 17Bases and Coordinates
  19. Chapter 18Orthogonality
  20. Chapter 19Rank
  21. Chapter 20Eigenvectors and Eigenvalues
  22. Chapter 21Symmetric Matrices and Covariance
  23. Chapter 22Principal Component Analysis
  24. Chapter 23The Singular Value Decomposition
  25. Chapter 24Matrices Built From Outer Products
  26. Chapter 25Low-Rank Approximation
  27. Chapter 26Linear Algebra Inside a Neural Network Layer
  28. Chapter 27Gradients as Vectors
  29. Chapter 28Embeddings
  30. Chapter 29Attention as Matrix Operations
  31. Chapter 30Matrix Factorisation for Recommendation
  32. Chapter 31Computation, Precision and Scale
  33. Chapter 32Convolutions as Linear Operations
  34. Chapter 33Softmax: From Scores to Probabilities
  35. Chapter 34Rotations and Positional Encoding
  36. Chapter 35Normalisation Layers
  37. Chapter 36Geometry in High Dimensions
  38. Chapter 37Linear Algebra in Code
  39. Chapter 38Tensors: Beyond Matrices
  40. Chapter 39Where to Go Next
  41. AppendixExercises
  42. GlossaryGlossary

Who this book is for

Learners who want to understand the mathematics of AI models: students, developers and analysts comfortable with school algebra.

Details

FormatPDF + web edition
Length80 pages (approx.)
Chapters39
LevelIntermediate
LanguageEnglish
TopicFundamentals
AuthorLatent Library Editorial

Keep reading

You may also like

All books
$11.99
Details