What is Neural Networks

Definition

Neural networks are machine-learning models inspired by the brain, composed of layers of interconnected nodes that transform inputs through weighted connections and activation functions, learning complex patterns from data to power tasks from image recognition to language understanding.

« Back to Glossary Index

Learn complex, non-linear patterns directly from data
Power advances in vision, language, speech, and more
Improve with scale of data and model size
Underpin deep-learning systems including modern AI models

Real World Example

A medical imaging team trains a neural network on labelled scans so it learns to detect tumours, recognising subtle patterns across layers that hand-crafted rules could never reliably capture.

FAQs

How do neural networks learn?

They adjust the weights of connections through training, minimising error so the network maps inputs to correct outputs.

What is deep learning?

It is the use of neural networks with many layers, enabling them to learn increasingly abstract features from data.

What are neural networks used for?

Image and speech recognition, natural language processing, recommendation, and as the basis of modern generative AI.