Machine Learning Foundations
A jargon-free introduction to what machine learning is, its three main types, and the data-to-model workflow behind every ML project.
Learning from data vs. writing rules
Two ways to get a computer to do a job For most of computing history, making a program do something meant one thing: a human sat down and wrote the rules. If the total is over $100, apply a discount. If the date is a weekend, charge the higher rate. This is traditional programming — […]
Garbage in, confident garbage out
Most failed ML projects fail at the data, not the model The public story of machine learning is about algorithms. The working reality is that teams spend most of their time on data, and almost every project that quietly dies does so because the data could not support the question — not because the model […]
When not to use machine learning
The most valuable ML skill is recognising the problems that are not ML problems Machine learning earns its cost when a rule is genuinely hard to write down and the pattern is genuinely in the data. Plenty of problems meet neither condition, and reaching for a model there buys you complexity, opacity and a maintenance […]
Your first honest ML conversation
Turning the whole course into one useful habit Whether you commission ML, work beside it, or are simply in the room, the same short frame turns a vague idea into a conversation that goes somewhere. The five questions, in order What decision changes? If no decision or action changes because of the prediction, there is […]