A neural network is built from simple units called nodes, or artificial neurons, arranged in layers. Each connection has a weight, and the network learns by adjusting those weights as it sees more training examples.
Data enters the first layer, passes through hidden layers that progressively detect patterns, and produces a result at the output layer. Early layers might detect edges in an image, later ones whole objects like faces.
Deep learning simply means a neural network with many hidden layers. This architecture underpins machine learning breakthroughs from image recognition to the large language models behind today's AI assistants.