F04 Stage A · Foundations 40 h (18 T / 22 P) Statutory
Mathematics & Statistics for AI
Reasons quantitatively about models and evidence.
Prerequisite
None
Modules
5
NOS
—
Statutory mapping
Model Curriculum Bridge Module 3
Tech stack
NumPySciPy
Modules
5 modules · 40 hours
M1 · Linear algebra
10 h TOPICS
- Vectors and matrices
- Matrix multiplication
- Transpose and inverse
- Identity and rank
- Eigenvalues and eigenvectors
- Norms
- Dot product and cosine similarity
Lab: Implement matrix operations and cosine similarity from first principles
Course material for this module is in production.
M2 · Calculus for optimisation
8 h TOPICS
- Derivatives and partial derivatives
- Chain rule
- Gradients
- Convexity
- Gradient descent and variants
Lab: Implement batch and stochastic gradient descent; visualise convergence
Course material for this module is in production.
M3 · Descriptive statistics
8 h TOPICS
- Mean, median, mode
- Dispersion and variance
- Standard deviation
- Skew and percentiles
- Statistical anomalies: missing values, bias, outliers
Lab: Statistical profile of a raw production dataset
Course material for this module is in production.
M4 · Probability
7 h TOPICS
- Sample spaces
- Conditional probability
- Bayes' theorem
- Independence
- Normal, binomial and Poisson distributions
- Central limit theorem
Lab: Bayesian update exercise on a classification prior
Course material for this module is in production.
M5 · Inferential statistics
7 h TOPICS
- Sampling
- Confidence intervals
- Hypothesis testing
- p-values
- Type I and II error
- Statistical power
- Correlation versus causation
Lab: Design and analyse a controlled comparison
Course material for this module is in production.
Real-world work scenario
A stakeholder claims a new feature lifted conversion by 12%. Determine whether the sample supports the claim, compute the confidence interval, identify the confound, and present a defensible verdict.
Assessment
Quiz + derivation set · applied statistics practical