Detailed explanation
Each neuron applies a linear combination followed by a non-linear function. Stacking layers learns increasingly abstract representations. The neural network is the building block of deep learning.
Examples
Multi-layer perceptron
CNN for vision
RNN for time series
Transformer for text
Frequently asked questions
How many layers?
From a few to several hundred depending on the task — 'deep' starts beyond a few hidden layers.
Related terms
Deep Learning
A subfield of machine learning using deep neural networks to learn complex representations.
Machine Learning
A branch of AI where models learn patterns from data instead of following explicit rules.
Transformer
A neural network architecture based on the attention mechanism, foundation of modern LLMs.
Last updated: 7/15/2026