Machine Learning Basics
MACHINE LEARNING (ML) is a kind of AI where computers learn from EXAMPLES instead of being given step-by-step instructions. Instead of writing rules like "if email contains lottery, mark as spam," you show the system thousands of spam emails and thousands of regular emails. The system figures out the patterns itself.
Three main types. SUPERVISED LEARNING: train on labeled examples (this is a cat, this is a dog) and predict on new ones. UNSUPERVISED LEARNING: find patterns without labels (group similar customers together). REINFORCEMENT LEARNING: learn from rewards and penalties (game-playing AIs, robotics). Most modern AI uses combinations of all three.
You want to build a system that detects whether an email is spam. Which type of machine learning would you use?
Important caveats. ML systems can ONLY be as good as their training data. Biased data → biased models. They can't reason about things they've never seen. They can be confidently wrong. They need huge amounts of data to learn anything complex. Despite this, ML powers Netflix recommendations, Google Search, fraud detection, medical diagnosis assistants, and most AI products today.
Try a Free Tool
Visit a free tool like Teachable Machine (teachablemachine.withgoogle.com). In 10 minutes, train a simple model to recognize three of your hand gestures. You'll see how training, testing, and predictions work in practice.
Machine learning is one of the most important technologies of our time. Knowing how it works at the basic level lets you understand what it can do — and where it goes wrong.
Want to keep learning?
Sign up for free to access the full curriculum — all subjects, all ages.
Start Learning Free