AI glossary · Machine learning
Neural network
A neural network is an AI model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.
Also called artificial neural network, ANN, neural net
In more detail
Each unit takes in numbers, combines them using adjustable weights, and passes a result to the next layer through an activation function. Training nudges the weights, using backpropagation, until the network’s outputs match the examples.
Networks with many layers are the basis of deep learning. Despite the name, they work very differently from real brains.
Related terms
Deep learningDeep learning is a type of machine learning that uses neural networks with many layers to learn complex patterns in text, images and sound.ParametersParameters are the internal numbers an AI model learns during training. A model’s size, such as “70 billion parameters”, counts them.BackpropagationBackpropagation is how a neural network learns from mistakes: it works backwards from the error to find how much each connection caused it, then adjusts them.Activation functionAn activation function decides how strongly each unit in a neural network passes its signal on, which lets the network learn complex, non-linear patterns.TransformerA transformer is the neural network design behind almost every modern language model. It reads a whole passage at once and works out how its words relate.
Browse related tools
AI tools listed on BroUseAI in these categories.
