Neural network
A type of machine learning system made of many simple connected units that pass numbers to each other. It is loosely inspired by how brain cells connect.
Picture a large web of tiny calculators arranged in layers. Each one takes in a few numbers, does a simple sum and passes the result on. The strength of each connection can be adjusted. During training, the network nudges millions or billions of these strengths until its outputs match the examples it was shown.
Neural networks are behind face unlock on phones, voice assistants that turn speech into text and the large language models that power chatbots. Networks with many layers are often called "deep learning".
The brain comparison is only loose. A neural network does not think or feel, and it works very differently from a real brain. It is also hard to see why a network gave a particular answer, because what it has learned is spread across a vast number of numbers rather than written as readable rules.
Related: Machine learning, Model (AI model), Large language model (LLM)