📚 Glossary
Neural network
In one line: The mathematical structure that LLMs are built from — billions of simple equations connected together to learn patterns.
A neural network is the mathematical structure underlying LLMs and most modern AI. It's a stack of layers, each containing simple equations (neurons), connected by weighted links.
Training a neural network adjusts those weights to make the network's outputs match the desired outputs on training data. With billions of parameters and trillions of training examples, neural networks learn to do remarkably general things — write essays, generate code, recognise images.
Modern LLMs use a specific neural network architecture called the transformer.
See it in action — ask any AI about neural network on AskAI.free.
Try it free →