Neural Network
A computational architecture loosely inspired by the brain, made of layered artificial neurons that learn patterns from data. The foundation of modern AI.
An artificial neural network is a computational system loosely inspired by the structure of biological neurons. It consists of layers of simple computational units ("neurons") that each compute a weighted sum of their inputs, apply a non-linear activation function, and pass the result to the next layer.
By stacking many layers (deep learning), neural networks can learn hierarchical features. Training adjusts the weights via backpropagation until the network reliably produces correct outputs for known inputs.
Neural networks underpin almost all modern AI: image recognition, speech recognition, language translation, generative models, and large language models. The transformer architecture, introduced in 2017, currently dominates natural language and many other domains.