Machine Learning Introduction

Definition: Machine Learning (ML) is teaching a computer to find patterns in data and make predictions or decisions — without being given step-by-step rules for every case.

Instead of a programmer writing "if this, then that" for every situation, you show the computer many examples and it learns the pattern itself. This powers spam filters, recommendations, voice assistants, and fraud detection.

The three main types

• Supervised learning — learn from labelled examples (data + the right answer), then predict answers for new data. e.g. predict house price from size.
• Unsupervised learning — find structure in data with no labels, e.g. group customers into segments.
• Reinforcement learning — learn by trial and error through rewards, e.g. a game-playing agent.

The big idea in one line

ML usually starts by finding patterns in numbers. Even a simple average is a tiny "model" of your data:

sales = [10, 12, 14, 16, 18]
avg = sum(sales) / len(sales)
print("Typical sale:", avg)

💡 Note: this course runs real Python in your browser. Later lessons use libraries like NumPy and scikit-learn — they download once on the first Run (a few seconds), then stay fast.