Mathematics & Statistics for AI

Every lesson: deep notes, curated lectures, an animated explainer, a hands-on lab, practice questions and a timed exam.

1. VectorsLab: ML math notebook lab. Assignment: Implement vector operations in NumPy.
2. Linear combinationsLab: Feature-space visualizer lab. Assignment: Visualize linear combinations.
3. Matrix multiplicationLab: Matrix calculator lab. Assignment: Implement matrix multiplication manually and with NumPy.
4. Eigenvalues/eigenvectorsLab: PCA intuition lab lab. Assignment: Relate eigenvectors to principal directions.
5. DerivativesLab: Gradient intuition lab lab. Assignment: Numerically estimate derivatives.
6. Partial derivativesLab: Multivariable gradient lab lab. Assignment: Compute partial derivatives for a loss function.
7. Chain ruleLab: Backprop precursor lab. Assignment: Trace derivatives through a two-layer function.
8. Gradient descentLab: Optimizer visualizer lab. Assignment: Implement gradient descent from scratch.
9. Probability fundamentalsLab: Probability simulator lab. Assignment: Simulate Bernoulli/binomial events.
10. Conditional probability/BayesLab: Bayes classifier lab lab. Assignment: Implement a simple Bayesian classifier.
11. Expectation and varianceLab: Distribution analysis lab. Assignment: Compute expectation/variance from data.
12. Correlation vs causationLab: Analytics critique lab. Assignment: Identify misleading correlations.
13. Sampling and confidence intervalsLab: Experiment analysis lab. Assignment: Build confidence intervals from samples.
14. Hypothesis testingLab: A/B test analysis lab. Assignment: Test a marketing/product hypothesis.
15. Math-to-ML checkpointLab: ML math diagnostic lab. Assignment: Explain where each math concept enters an ML pipeline.

Tools introduced: scikit-learn