Machine Learning
A way of getting a computer to learn patterns from lots of examples rather than being given step-by-step instructions for every situation. Show it thousands of photos of cats and it works out for itself what a cat tends to look like. This approach is called machine learning, and it sits underneath almost every AI tool you use today.
For most of computing history, people told computers exactly what to do, one precise rule at a time. Machine learning turns that around. Instead of writing out every rule, you show the computer a huge number of examples and let it spot the patterns on its own. The name captures the idea nicely: the machine is learning from what it sees.
Think about how a child learns to recognise a dog. Nobody hands them a checklist of ears, tails, and fur. They see plenty of dogs, hear the word “dog”, and gradually the idea forms. Machine learning works in a similar spirit. The examples it learns from are called training data, and the more varied and plentiful they are, the better the result tends to be.
This matters to you because it explains why AI can feel surprisingly capable in some areas and oddly patchy in others. An AI is only as good as the examples it learned from. If it saw very little of something during training, it may struggle with it, even when the task seems easy to you.
Machine learning is the broad family of techniques behind the AI tools you use. One especially powerful member of that family, the neural network, powers the chat assistants most people have met. When you hear that an AI was “trained”, machine learning is what that training refers to.