Machine Learning
Machine learning is when computers improve at a task by finding patterns in large amounts of data rather than following fixed rules.
▶ Interact
Play with the controls to see the idea in action.
📘 Learn
Machine learning is when computers improve at a task by finding patterns in large amounts of data rather than following fixed rules.
- Training data teaches the model
- More data often improves results
- Bias in data produces biased results
🧠 Quick quiz
Three questions. Score 2 or more to complete the topic.
What is Machine Learning?
Within Computer Science, which covers algorithms, programming, data, networks, hardware and safe, responsible use of technology, this topic explains Machine Learning. Computing topics explain how software, hardware and data work, with diagrams and models that show each step in order.
Check that you can explain Machine Learning in your own words and give one example from everyday life. If you can do that, you have understood the core idea.
Understanding Machine Learning helps you design, test and explain programs, websites and systems, from small projects to exam questions.
Machine Learning in detail
Machine learning is a branch of AI in which computers learn patterns from data and improve with experience, without being explicitly programmed for every case. In supervised learning, the system learns from labelled examples (such as emails marked spam or not) to predict labels for new data. Unsupervised learning finds hidden groups in unlabelled data, and reinforcement learning learns by trial, reward and penalty.
The process involves collecting data, training a model, testing it on new data and refining it. Neural networks, inspired by the brain, are used for images and language. Results depend on the quality and fairness of the data, as biased data gives biased results.
How the interactive helps you understand Machine Learning
Watch the growth curve in the interactive. Use any sliders or buttons it offers to change the values and see how the growth curve responds.
Before you change anything, predict the result. Then change one value at a time and check whether your prediction was right. This is a quick way to build a correct mental model of Machine Learning.
Real-life uses and examples
- Apply Machine Learning when you design a small program, website or spreadsheet.
- Explain Machine Learning to someone new to computing by comparing it to a familiar process.
- Trace through a process that uses Machine Learning to check what it does step by step.
Common mistakes to avoid
- Testing only the normal case and forgetting the edge cases.
- Using the term without being able to say what the computer actually does.
- Learning the definition without testing it. Use the quiz and the interactive to check that you can apply the idea.
Frequently asked questions about Machine Learning
What is Machine Learning?
Machine learning is when computers improve at a task by finding patterns in large amounts of data rather than following fixed rules.
What are the most important points about Machine Learning?
The main points are: Training data teaches the model; More data often improves results; Bias in data produces biased results.
Why is Machine Learning useful?
Understanding Machine Learning helps you design, test and explain programs, websites and systems, from small projects to exam questions.
How can I practise Machine Learning?
Open the interactive at the top of this page and change the controls one at a time. Predict the result before each change, then take the three-question quiz. A score of two or more marks the topic as complete on this device.
Which topics are related to Machine Learning?
Related topics in Computer Science include SQL Basics, Digital Sound, Alan Turing and Ada Lovelace.