← Back to tracks

Mathematics for Artificial Intelligence

The mathematical backbone of machine learning, from vectors to optimization.

A cross-cutting track that gathers, in the order you actually need them, all the mathematics required to understand and build learning models: linear algebra, differential calculus, probability, statistics, optimization and information theory.

For Developers and self-taught learners aiming for machine learning who want solid mathematical foundations, from high school to graduate level.

20 courses

High school 2 courses
  • 01 Vectors and analytic geometry
    Linear algebra Coming soon
  • 02 Discrete probability
    Probability and statistics Coming soon
Preparatory class 5 courses
  • 01 Linear systems and matrices
    Linear algebra Coming soon
  • 02 Vector spaces and linear maps
    Linear algebra Coming soon
  • 03 Eigenvalues and diagonalization
    Linear algebra Coming soon
  • 04 Riemann integration
    Real analysis Coming soon
  • 05 Random variables and continuous laws
    Probability and statistics Coming soon
Bachelor 7 courses
  • 01 Euclidean spaces and SVD
    Linear algebra Coming soon
  • 02 Multivariable calculus
    Differential calculus Coming soon
  • 03 Limit theorems
    Probability and statistics Coming soon
  • 04 Measure and Lebesgue integration
    Measure theory Coming soon
  • 05 Inferential statistics
    Statistics Coming soon
  • 06 Numerical analysis
    Numerical methods Coming soon
  • 07 Graph theory
    Graph theory Coming soon
Master 6 courses
  • 01 Bayesian statistics
    Statistics Coming soon
  • 02 Convex optimization
    Optimization Coming soon
  • 03 Stochastic optimization
    Optimization Coming soon
  • 04 Information theory
    Information theory Coming soon
  • 05 Hilbert and Banach spaces Optional
    Functional analysis Coming soon
  • 06 Curves, surfaces and manifolds Optional
    Differential geometry Coming soon