A neural network is a machine-learning model made of connected layers that transform input into output.
A neural network contains connected computational units whose learned parameters transform information through layers.
Neural networks were historically inspired in part by biological neurons, but modern artificial neural networks are mathematical systems, not digital brains.
A series of adjustable filters.
Maps visual patterns in an image to a label such as “cat,” “road,” or “defect.”
Maps text patterns to categories such as topic, sentiment, or spam.
Maps relevant features to an estimated price or other numeric value.
It is a mathematical model that learns numerical transformations, not a biological mind.
Deep learning usually uses neural networks with many layers; the terms are related but not identical.
A network connects many computational units and layers, rather than being a single unit.
Deep Learning usually uses multi-layer neural networks, but Neural Network and Deep Learning are not completely synonymous.
Explore next
A neural network learns adjustable numerical transformations that map inputs to outputs.
A dedicated neural-network explainer will be added when a real video asset is available.