Machine Learning
In simple words
Systems whose behaviour is learned from data rather than written as rules.
The fuller explanation
Traditional software encodes a human's rules. Machine learning inverts that: you supply examples of the input and the desired output, and an optimisation procedure searches for a function that maps between them.
That inversion is the whole idea, and it buys you the ability to solve problems nobody can write rules for. It also costs you something real. The behaviour of the resulting system is not written down anywhere a person can read, its quality is bounded by the data you fed it, and it will fail in ways your test set never showed you.
Three families cover most of it. Supervised learning learns from labelled examples and is the overwhelming majority of production ML. Unsupervised learning finds structure in unlabelled data. Reinforcement learning learns from a reward signal over time. Start with supervised, get genuinely good at evaluation, and treat everything else as a specialisation.
Learn these first
Real prerequisites, taken from the map rather than guessed.
Sources
Where this came from, so you can go past us.
Where does this sit on your route?
The free assessment places you on the same map and names which terms stand between you and the role you want.
Take the free assessmentSee it in context
The Atlas shows this term with everything that leads into it and everything that follows, as one picture.
Open the map