AI & Programming Foundations
Mathematics and Statistics for AI
F02 · Foundation
Entry requirements
F01 or equivalent Python skills
What 24 hours means
- Lessons
- 18 h
- Capstone
- 4 h
- Assessment
- 1 h
- Remediation
- 1 h
Syllabus
Four modules, twelve lessons. Every lesson states what it covers and the evidence you produce for it.
Module 1
Vectors and functions
Vectors and dimensions · Matrix operations · Functions and rates of change
F02Show lessonsHide lessons
F02.01 · 90 min
Vectors and dimensions
Represent learners as feature vectors and check compatible matrix shapes.
Evidence: Correct dimensions for three matrix operations with explanations.
F02.02 · 90 min
Matrix operations
Implement dot products and transformations on a small dataset.
Evidence: Manual and notebook results agree within floating-point tolerance.
F02.03 · 90 min
Functions and rates of change
Module 2
Probability
Probability and conditional events · Distributions and simulation · Bayesian updating
F02Show lessonsHide lessons
F02.04 · 90 min
Probability and conditional events
Calculate conditional probabilities from a contingency table.
Module 3
Statistical reasoning
Sampling and bias · Estimation and intervals · Hypothesis testing
F02Show lessonsHide lessons
F02.07 · 90 min
Sampling and bias
Compare random and convenience samples from a known synthetic population.
Module 4
Optimisation
Loss functions · Gradient descent · Statistics review
F02Show lessonsHide lessons
F02.10 · 90 min
Loss functions
Compute squared error and cross entropy for supplied predictions.
Evidence:
Capstone
Analyse a synthetic learning-outcome dataset and compare two interventions without overstating causality. Submit calculations, plots, uncertainty estimates and a decision memo.
Lab environment
CPU notebook
Lab infrastructure is not yet provisioned, so this describes the environment the course is designed for rather than one you can launch today.