28 — Mathematics & Statistics¶
The math behind the models: linear algebra, calculus, probability, statistics, and optimization.
Scope¶
Cheat sheets for the mathematical and statistical foundations used across data science, machine learning, and deep learning — formulas, terminology, interpretation, and Python where useful.
Cheat Sheets¶
| Cheat Sheet | Description |
|---|---|
| linear-algebra.md | Vectors, norms, matrices, eigenvalues, SVD, decompositions — the math of PCA, least squares, and embeddings |
| calculus.md | Derivatives, gradients, the chain rule in backprop, Hessians, Taylor, convexity |
| probability.md | Conditional probability, Bayes' rule, expectations, variance/covariance, CLT, information theory |
| statistics.md | Descriptive stats, sampling, estimators, SEs, confidence intervals, bias–variance |
| optimization.md | Gradient descent, SGD/Adam, learning-rate schedules, regularization as constraints, hyperparameter search |
| hypothesis-testing.md | $H_0$/p-values, Type I/II errors, test selection tables, multiple comparisons, scipy recipes |
| statistical-distributions.md | The distributions used in ML: Bernoulli→Normal, Beta, Poisson, chi2, t, F — moments and scipy usage |
Contribute¶
- Template: CHEATSHEET_TEMPLATE.md
- Guide: CONTRIBUTING.md