Math
Foundational mathematics for machine learning — linear algebra, calculus, probability, and visualization progressing from manual Python implementations to NumPy and Matplotlib.
Modules
| Module | Description | Files |
|---|---|---|
| Linear Algebra | Matrix operations: slicing, shape, transpose, element-wise ops, concatenation, multiplication — manual → NumPy | 19 tasks |
| Advanced Linear Algebra | Determinant, minor, cofactor, adjugate, inverse, definiteness — pure Python → NumPy verification | 7 tasks |
| Calculus | Derivatives, partial derivatives, integrals, definite/indefinite, double integrals | 17 tasks |
| Bayesian Probability | Likelihood, intersection, marginal, posterior probability with NumPy | 4 tasks |
| Plotting | Matplotlib: line, scatter, bar, frequency, all-in-one, gradient descent, PCA | 9 tasks |
| Probability | Statistical distributions: binomial, normal, poisson, exponential | 4 tasks |
Learning Path
- Python Slicing (Tasks 0–1): Master array indexing and 2D extraction
- Manual Matrix Operations (Tasks 2–8): Build intuition with nested loops — shape, transpose, add, concat, multiply
- NumPy Transition (Task 9): First contact with NumPy arrays and transpose
- NumPy Vectorization (Tasks 10–14): Replace loops with built-in methods — shape, transpose, broadcasting,
@operator - Advanced Generalization (Tasks 100–102): N-dimensional operations with recursion,
sliceobjects, tuple indexing - Advanced Linear Algebra (det → minor → cofactor → adjugate → inverse → definiteness)
- Calculus (derivatives → partial derivatives → integrals → double integrals)
- Probability & Bayesian (distributions → likelihood → posterior)
- Visualization (basic plots → gradient descent → PCA)