A subset of machine learning that uses neural networks with many layers (hence "deep") to learn hierarchical representations of data. Each layer transforms its input into something slightly more abstract — from pixels to edges to shapes to objects to concepts. Deep learning is what made the modern AI revolution possible: it's the approach behind LLMs, image generators, speech recognition, and virtually every AI breakthrough since 2012.
Why it matters
Deep learning is the engine of the current AI era. Before 2012, AI was a patchwork of specialized algorithms. Deep learning unified everything under one paradigm: stack enough layers, feed enough data, throw enough compute at it, and the model figures out the rest. Understanding deep learning is understanding why AI suddenly works.