Deep learning

Deep learning is a variant of machine learning ✕ Machine learning is the branch of AI in which a system learns from examples instead of following hand-coded rules. The more data, the better it generalizes. More in the glossary → that uses artificial neural networks ✕ A neural network is an AI model loosely inspired by the brain, made of connected nodes that adjust as they learn. It is the basis of deep learning. More in the glossary → with many stacked layers —hence "deep." Each layer transforms the data and detects increasingly abstract features: in an image, the first layers see edges and colors, and the last ones see whole objects such as a face. This ability to learn representations on its own is what has driven the recent big leaps in vision, speech and language, including the models that generate text and images. In exchange, it needs a lot of data and enormous computing power, usually with specialized graphics cards. It is the technology behind almost all the AI ✕ Artificial intelligence is a computer system’s ability to perform tasks we associate with human intelligence, such as understanding language, recognizing images or making decisions. More in the glossary → people talk about today.