Math Foundations

Mission. Teach the mathematics that the NumPy/pandas/scikit-learn stack silently assumes.

Scope

Learning objectives

Lessons

This track is scaffolded and waiting for content. See the curriculum dashboard for the roadmap and progress across all tracks.

Planned lessons (24)

Wave 2 — breadth (provisional roadmap) — 24 lessons

linear-algebra

  • Vectors concept · beginner · S Magnitude and direction as the atom of data representation.
  • Dot Products and Similarity concept · beginner · S Projections, cosines, and why similarity is a dot product.
  • Norms and Distances concept · beginner · S Measuring size: L1, L2, and what each is for.
  • Matrices as Transformations concept · beginner · M A matrix is a verb: stretching, rotating, projecting space.
  • Matrix Multiplication, Geometrically concept · intermediate · M Composing transformations, and why the order matters.
  • Linear Systems concept · intermediate · M Elimination, solution sets, and the geometry of solvability.
  • Rank, Span, Independence concept · intermediate · M The dimensions of your data and the redundancies inside it.
  • Determinants concept · intermediate · S What a determinant measures: volume, orientation, invertibility.
  • Eigenvalues and Eigenvectors concept · advanced · M The directions a transformation doesn't turn, and why ML keeps finding them.
  • Singular Value Decomposition concept · advanced · M The workhorse decomposition behind PCA, compression, and recommender systems.
  • Projections and Least Squares concept · advanced · M The geometry behind every regression you'll fit.

probability

  • Sample Spaces and Events concept · beginner · M Counting outcomes correctly before reasoning about them.
  • Conditional Probability and Bayes concept · intermediate · M Updating beliefs when evidence arrives, done carefully.
  • Expectation and Variance concept · intermediate · M The mean as an operator, and variance as its second moment.
  • Covariance and Correlation concept · intermediate · M Joint behavior of random variables, from the math up.

calculus

  • Derivatives as Sensitivity concept · beginner · S Rates of change: what nudging an input does to an output.
  • Gradients concept · intermediate · M Partial derivatives as a vector pointing uphill.
  • The Chain Rule concept · intermediate · M Derivatives through composition, the engine of backpropagation.

optimization

  • Convexity concept · intermediate · M Bowl-shaped problems you can actually solve to optimality.
  • Gradient Descent by Hand concept · intermediate · M Deriving and stepping the update rule yourself.
  • Gradient Descent in NumPy example · intermediate · M The update rule in code, with diagnostics for divergence.
  • Constrained Optimization concept · advanced · M Lagrange multipliers and the boundary of the feasible set.

discrete

  • Counting and Combinatorics concept · intermediate · M Permutations, combinations, and counting without listing.
  • Graph Theory Essentials concept · intermediate · M Nodes, edges, paths: the structures behind networks and pipelines.