The basics
Deep learning is machine learning that uses neural networks with many layers, so a computer can learn very complex patterns from huge amounts of data.
A neural network is a program loosely inspired by the brain. It is built from layers of tiny math units that pass signals to each other. 'Deep' simply means many layers stacked up, sometimes hundreds. Each layer learns to notice something slightly more abstract than the layer before it.
In a picture, early layers might notice edges and colors. Middle layers combine those into shapes like eyes or wheels. Late layers recognize whole objects such as a face or a bicycle. Nobody programs these steps. They emerge on their own when the network is trained on millions of examples.
Deep learning took off around 2012, when powerful graphics chips made training large networks practical. Today it powers speech recognition, translation, image generation, and the large language models behind chatbots. Almost every headline AI system since then has been deep learning.
When a photo app groups pictures of the same friend across ten years of changing haircuts and glasses, a deep network is recognizing that face.