AI vs. ML vs. Deep Learning

Artificial intelligence (AI) is the broad goal of building systems that act intelligently: perceive, reason, plan, understand language. Early AI was mostly hand-written rules and search — chess engines, expert systems, route planners.

Machine learning (ML) is the part of AI where behaviour is learned from data instead of being programmed rule by rule. You supply examples and an objective; an algorithm adjusts a model's parameters until it performs well on the examples and, hopefully, on new ones.

Deep learning (DL) is the part of ML that uses neural networks with many layers. Each layer turns its input into a slightly more abstract representation — pixels → edges → shapes → objects — so the network learns its own features instead of relying on hand-crafted ones.

Deep learning took over vision, speech and language after 2012 because three things came together: very large labelled datasets, GPUs that make matrix maths fast, and better training tricks (ReLU, dropout, batch normalisation, residual connections).