Deep learning: definition

Deep learning is machine learning that uses many-layered neural networks to learn complex patterns, and it is the approach behind most modern AI breakthroughs.

Deep learning stacks many layers of artificial neurons so the system can learn increasingly abstract patterns, edges, then shapes, then objects in an image, for example. The "deep" just means many layers.

It is the engine behind image recognition, speech, and large language models. It needs a lot of data and computing power, which is why these capabilities arrived only once both became cheap enough.

Related terms

Neural network: A neural network is a computing system loosely inspired by the brain, made of layers of connected nodes that adjust their strengths as they learn from data.
Machine learning: Machine learning is a branch of AI where a system learns patterns from data and improves at a task through examples, instead of being programmed with explicit rules.
Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.