Theory
Eleven short lessons in a sensible order. Each one has something to play with, a few terms explained in plain words, and a three-question check at the end. No coding needed.
AI, machine learning, deep learning, GenAI: which is which
Four words that get used as if they mean the same thing. They don’t, and the difference decides what a tool can and cannot do.
Lesson 2How a machine learns, and how it fools itself
Training, testing, overfitting and data leakage, with a model you can bend until it breaks.
Lesson 3Neural networks: one neuron, then millions
What a weight is, what training changes, and why a learning rate can make or break a model.
Lesson 4Sensitivity, specificity, PPV: the numbers that decide if you trust an alert
Same model, different ward, very different usefulness. Play with prevalence and watch the false alarms.
Lesson 5ROC curves, AUC and the cut-off nobody tells you about
Why a great AUC can still mean a poor tool, and what calibration adds.
Lesson 6How ChatGPT, Claude and Gemini actually work
Tokens, next-word prediction, temperature, context windows, and why hallucination is built in.
Lesson 7RAG and agents: giving the model your documents and tools
How retrieval grounds an answer in your protocol, and what changes when the AI can take actions.
Lesson 8Prompting well, and keeping patients out of the chatbot
A five-part prompt you can reuse, and a checker that catches names, phone numbers and UHIDs before you paste.
Lesson 9Bias, dataset shift and how good tools fail
Why an AI that worked in Boston may not work in Bilaspur, and the human side: automation bias.
Lesson 10Reading an AI paper in 15 minutes
The reporting guidelines journals now expect, and twelve questions that sort strong evidence from hype.
Lesson 11Rules: India, the US and Europe
CDSCO, DPDP, ICMR, NMC, FDA and the EU AI Act, what each covers and where things stand in 2026.