AI & Engineering Academics›🌱 AI Seeds›Lessons›How Machines Learn

🧠

AI Seeds • Beginner⏱️ 12 min read

How Machines Learn

How Machines Learn 🧠

In the last lesson, we learned that AI is software that learns from experience. But how does that actually work? How does a machine go from knowing nothing to recognising your face or recommending your next favourite song?

Let's explore the secret behind smart software.

🔄 The Learning Loop

Every machine learning system follows the same basic cycle:

Data - The machine is given lots of examples
Patterns - It looks for recurring patterns in those examples
Predictions - It uses those patterns to make guesses about new data
Feedback - It finds out whether its guesses were right or wrong
Improvement - It adjusts and tries again, getting better each time

Think of it like learning to cook. You follow recipes (data), notice what works (patterns), try your own variations (predictions), taste the result (feedback), and adjust the seasoning next time (improvement).

Circular diagram showing the machine learning loop: Data flows to Pattern Recognition, then to Prediction, then to Feedback, then to Improvement, which loops back to Pattern Recognition — The machine learning cycle: data, patterns, predictions, feedback, and continuous improvement

🤯

Google's AI for detecting spam email processes over 10 million suspicious messages every minute. Each time a user marks something as "spam" or "not spam," the system learns and updates its patterns - getting smarter with every click.

📚 Supervised Learning - Learning with a Teacher

The most common type of machine learning is called supervised learning. It works exactly like studying with a teacher who gives you the answers.

Here's how it works:

You give the machine thousands of examples with labels (the correct answers)
The machine studies these labelled examples
It learns the patterns that connect the input to the correct label
When it sees new, unlabelled data, it predicts the answer

Real-World Example: Email Spam Filter

Imagine you show the machine 100,000 emails. Each one is labelled either "spam" or by humans.

Lesson 2 of 170% complete

←What is AI? A Friendly Introduction

Discussion

Suggest an edit to this lesson

The machine notices patterns:

Emails with "WIN FREE MONEY" tend to be spam
Emails from contacts in your address book tend to be genuine
Emails with dozens of exclamation marks are often spam

After studying enough examples, it can look at a brand new email it's never seen and predict whether it's spam - without anyone writing specific rules.

🤔

Think about it:

Supervised learning depends on labelled data - someone has to provide the correct answers for the machine to learn from. Who do you think labels all that data? In many cases, it's thousands of human workers carefully tagging images, text, and audio. The "intelligence" of AI often starts with a lot of human effort.

🧠Quick Check

What does 'supervised learning' mean in machine learning?

🔍 Unsupervised Learning - Finding Hidden Patterns

What if you don't have the answers? What if you just have a big pile of data and you want the machine to find interesting patterns on its own?

That's unsupervised learning. There's no teacher, no labels, no correct answers. The machine explores the data and groups similar things together.

Real-World Example: Customer Grouping

Imagine a supermarket has purchase data for millions of customers, but no labels. The AI analyses the data and discovers natural groups:

Group A: Buys organic vegetables, free-range eggs, and oat milk
Group B: Buys frozen pizzas, crisps, and fizzy drinks
Group C: Buys nappies, baby food, and wet wipes

Nobody told the machine these groups existed. It found them on its own by spotting patterns in the shopping data. The supermarket can now send each group relevant offers.

🧠Quick Check

How does unsupervised learning differ from supervised learning?

🐕 Reinforcement Learning - Trial and Error

The third type is reinforcement learning, and it works a lot like training a dog.

When a dog sits on command, you give it a treat (reward). When it chews your shoe, you say "no" (penalty). Over time, the dog learns which behaviours lead to treats and which lead to trouble.

Reinforcement learning works the same way:

The AI takes an action in an environment
It receives a reward (positive) or penalty (negative)
It adjusts its strategy to maximise rewards over time
It tries millions of different approaches until it finds the best one

Real-World Example: Game-Playing AI

Google's AlphaGo learned to play the ancient board game Go by playing millions of games against itself. Each win was a reward; each loss was a penalty. It tried wild strategies, learned from failures, and eventually became better than any human player in history.

The same approach is used to train robots to walk, teach self-driving cars to navigate, and optimise energy use in data centres.

🤯

AlphaGo played over 30 million games against itself during training. A human playing one game per day would need about 82,000 years to play that many games. The AI compressed all that experience into just a few weeks.

🗺️ Comparing the Three Types

| Type | Has Labels? | Analogy | Example | |------|------------|---------|---------| | Supervised | Yes | Studying with an answer key | Spam filters, medical diagnosis | | Unsupervised | No | Sorting a messy drawer | Customer grouping, anomaly detection | | Reinforcement | No (uses rewards) | Training a dog with treats | Game AI, robotics, self-driving cars |

🤔

Think about it:

Think about how you learned to ride a bicycle. Was it supervised (someone told you exactly what to do), unsupervised (you figured out balance on your own), or reinforcement (you fell, adjusted, and tried again)? Most human learning is actually a mix of all three. AI learning styles are inspired by how we learn ourselves.

Machines learn through a cycle: data → patterns → predictions → feedback → improvement
Supervised learning uses labelled examples - like studying with a teacher
Unsupervised learning finds hidden patterns in data without labels
Reinforcement learning uses rewards and penalties - like training a dog
All three types power the AI systems you use every day

🧠Quick Check

Which type of machine learning is most like training a pet with treats and commands?

💡

You don't need to be a mathematician or programmer to understand machine learning. At its core, it's about learning from experience - something every human does naturally from the day they're born. AI just does it with data instead of life experiences.

Now that you understand how machines learn, the next lesson reveals the AI that's already in your pocket. Your smartphone is packed with intelligent features - let's uncover them.

AI Foundations

AI Mastery

Career Ready

Lab

How Machines Learn

How Machines Learn 🧠

🔄 The Learning Loop

📚 Supervised Learning - Learning with a Teacher

Real-World Example: Email Spam Filter

Discussion

🔍 Unsupervised Learning - Finding Hidden Patterns

Real-World Example: Customer Grouping

🐕 Reinforcement Learning - Trial and Error

Real-World Example: Game-Playing AI

🗺️ Comparing the Three Types

🔑 Key Takeaways

What's Next?