ML Fundamentals

What a machine learning system actually is — a pipeline from raw data to feedback — and the sixteen things that go wrong in it, most of which are invisible offline.

What ML Engineering Is

Not "which algorithm". Turning data into a system that learns useful patterns, generalises, serves predictions and stays measurable after it ships — and knowing which neighbouring domain owns each thing it depends on.

Q · A team has a notebook with a good model in it. What is the distance between that notebook and a system the business can rely on, and which of it is ML engineering's job?
The ML Pipeline
▶ lab

Raw data → dataset → features → split → model → training → evaluation → artifact → deployment → inference → feedback. Eleven stages, each a place an assumption enters, and the loop back is what makes it a system rather than a script.

Q · What are the stages between an event happening in the world and a model influencing the next such event, and what does each stage decide that the model can no longer change?
What Can Go Wrong
▶ lab

Sixteen failure classes, each entering at a specific pipeline stage, most invisible to the offline metric. Learning to name them by stage is the difference between debugging a model and retraining it in the dark.

Q · The model was fine at approval and is wrong in production. Which of the sixteen ways this happens entered at which stage, and which signal would have shown it?
Learning vs Programming

A program encodes rules someone wrote. A model encodes patterns from data it was shown — and therefore inherits the data's biases, gaps and timing. The model is a set of assumptions with weights attached.

Q · What is actually different about a component whose behaviour was learned from data rather than written as rules, and what does that difference do to testing, review and change?
The ML Reasoning Loop
▶ lab

Problem → Target → Data → Representation → Split → Model → Training → Evaluation → Validation → Deployment → Inference → Monitoring → Drift → Retraining. Fourteen questions in order, and the order is the method.

Q · Given any ML problem, incident or number, what is the sequence of questions that locates it, and why does skipping an early one invalidate every later answer?
Don't Delegate Understanding

Libraries hide optimisation, AutoML hides search, feature stores hide synchronisation, model servers hide inference, cloud platforms hide infrastructure, foundation models hide training. Use all of them — and know what each one is hiding when it breaks.

Q · Every layer of ML tooling hides something on purpose. Which things must the engineer still understand about a model they did not write, and what does "Model Accuracy = 94%" need before it means anything?