Prof by Lex AI Labs — home
Profby Lex AI
CurriculumPracticeFor OrganizationsPricing
Sign In
Start Your AI JourneyFree to start · No credit card required
FoundationsVisionSequencesTransformersAgentic AISystem DesignPracticeInterviewAI Dev

Math for ML

Linear Algebra for ML0/15
  • What a vector actually is
  • Adding, scaling, span
  • Length, distance, normalization
  • Dot product, angle, projection
  • A matrix is a function
  • Matrix–vector multiplication
  • Matrix multiplication and the transpose
  • Rank, collapse and the matrix inverse
  • Tensors, axes and broadcasting
  • Least squares and the normal equation
  • Change of basis
  • Eigenvectors and eigenvalues
  • The covariance matrix and eigendecomposition
  • Singular value decomposition and low-rank approximation
Calculus for ML0/6
  • Rate of change and the derivative
  • Derivative rules for ML
  • The chain rule
  • Partial derivatives and the gradient
  • The Jacobian and products of derivative matrices
Courses/math/Linear Algebra for ML/Tensors, axes and broadcasting
Reading progress

0% read

Course progress
0 / 21 lessons

Math for ML

On this page

No sections yet.

Up next

Least squares and the normal equation

Continue