Models & Architectures
Glossary
Neural Network
A computing model made of connected nodes organised in layers that learn by adjusting the strength of their connections.
Last updated
A neural network is inspired by the way biological neurons connect. Each node receives numbers, applies weights and a bias, then passes the result through an activation function to the next layer. During training, an algorithm such as backpropagation nudges those weights so the network produces better answers. A network with several hidden layers is called a deep neural network, the foundation of most modern AI.
Related terms
Deep Learning
Machine learning that uses multi-layered neural networks to learn complex patterns directly from raw data.
Parameters
The internal numbers a model learns during training; their count is a rough measure of model size.
Transformer
A neural network architecture that uses self-attention to weigh the importance of every word in a sequence relative to e...
Keep exploring
Browse the full AI glossary or compare AI tools that use this technology.