AI Model Creation Labs (Beginner → Advanced)
Six build-it-yourself labs: collect data, train a classifier by hand, tune a model, understand neural networks, prompt and evaluate an LLM, and ship a fair, tested AI system.
- 70
Lesson 1
Lab 1 — Build a Training Dataset
Every model starts with data. Design labels, collect balanced examples and spot the bias before you train anything.
- 110
Lesson 2
Lab 2 — Train a Classifier By Hand
Run a tiny Naive Bayes model with pencil and paper, then in code, so you can see exactly how 'learning' happens.
- 120
Lesson 3
Lab 3 — Tuning, Overfitting and Honest Evaluation
Diagnose a model that memorised its homework: learning curves, regularisation, cross-validation and baselines.
- 150
Lesson 4
Lab 4 — Build a Neuron, Then a Network
Weights, bias, activation and gradient descent — worked by hand on a 2-input neuron, then scaled up.
- 150
Lesson 5
Lab 5 — Prompting and Evaluating a Language Model
Treat an LLM like a component: write a spec prompt, build a test set, score the outputs and catch hallucinations.
- 200
Lesson 6
Lab 6 — Practical Exam: Ship a Fair Model
200 XP end-to-end exam: take a brief, plan the data, pick the model, evaluate honestly, audit for bias and write a model card.