The big picture

Artificial Intelligence (AI) is the broad goal of building systems that perform tasks we'd call "intelligent." Machine Learning (ML) is the dominant way we get there today: instead of hand-coding rules, we let a model learn patterns from data. Deep Learning is a powerful subset of ML that uses multi-layered neural networks.

Think of them as nested circles: Deep Learning ⊂ Machine Learning ⊂ Artificial Intelligence.

How ML differs from traditional programming

• Traditional code: you write the rules → the program produces answers.
• Machine learning: you provide examples (data + answers) → the model learns the rules.

Three families of ML

• Supervised learning — learn from labeled examples (spam / not-spam).
• Unsupervised learning — find structure in unlabeled data (customer segments).
• Reinforcement learning — learn by trial and reward (game-playing, robotics).

Key takeaway: ML is pattern-recognition at scale. The quality of your data matters more than the cleverness of your algorithm.