- Define and explain How Machine Learning Works in your own words
- Use key terms such as machine learning accurately
- Apply what you have learned to new examples and questions
- Avoid the common mistakes learners make with this topic
Modern AI does not follow hand-written rules — it learns patterns from enormous piles of data. That makes it powerful, but also unpredictable: an AI is only as fair and reliable as the data it was fed. This chapter looks under the bonnet of machine learning and asks the hard questions about using it well.
This lesson focuses on How Machine Learning Works: see how models learn patterns from data instead of following coded rules.
See how models learn patterns from data instead of following coded rules.
Key ideas
Learning replaces hand-written rules
Nobody could write rules to recognise every cat photo, so instead a model is shown thousands of labelled examples and adjusts its internal numbers until it predicts well. This is training; the model's skill is then tested on new examples it has never seen. If it only memorises the training set — overfitting — it fails on anything new.
Biased data in, biased decisions out
A hiring tool trained on a decade of a company's past hires will learn to prefer the kind of people the company used to hire — baking old discrimination into new software. Because the bias hides inside millions of tuned numbers, it is hard to spot without deliberately testing for fairness across groups.
Key term — machine learning: A branch of AI where programs improve at a task by finding patterns in data, rather than by following explicitly programmed rules.
What is the difference between traditional programming and machine learning?
In traditional programming humans write explicit rules; in machine learning the program finds its own patterns by training on data.
Answer: In traditional programming humans write explicit rules; in machine learning the program finds its own patterns by training on data.
- Assuming AI is neutral because maths is neutral Correction: models inherit the biases of their training data — neutrality must be tested for, never assumed.
- Trusting a high accuracy score without asking what it was tested on Correction: always ask whether the test data was balanced and representative — 98% on easy data can hide total failure elsewhere.
Practice
Overfitting is when a model memorises training examples instead of learning general patterns; it shows as high training accuracy but poor accuracy on unseen test data.
Its training data contains no night-time patterns, so it never learned the features of dark images — it can only recognise what it has seen.
False — remaining details like postcode or school can act as proxies for protected characteristics, so bias can survive.
The model may learn to prefer applicants resembling past successful ones, entrenching old biases against under-represented groups.
Quick check
Which of these best defines "machine learning"?
You use an AI chatbot to draft your history essay. What is the responsible way to handle this?
- How Machine Learning Works: see how models learn patterns from data instead of following coded rules.
- Learning replaces hand-written rules: Nobody could write rules to recognise every cat photo, so instead a model is shown thousands of labelled examples and adjusts its internal numbers until it predicts well.
- training data: The examples a model learns from — thousands of labelled photos, texts or records.
- Watch out for: assuming AI is neutral because maths is neutral