Neural Networks
Explore the brain-inspired technology behind face recognition, voice assistants, and more.
1. Inspired by the brain
Your brain contains billions of neurons that send signals to each other. A neural network copies this idea using artificial "neurons" — small math functions connected together.
2. Layers
Neural networks are arranged in layers. The first layer takes in data (like pixels of a photo), middle layers find features (edges, shapes, eyes), and the last layer gives an answer ("This is a face").
3. Learning from mistakes
When the network gets an answer wrong, it adjusts the strength of its connections slightly. After millions of adjustments, it becomes very accurate.
4. Deep learning
Networks with many layers are called "deep" neural networks, and using them is called deep learning. Deep learning powers today's most advanced A.I.
Field Vocabulary
The result of training — a system that uses learned patterns to make decisions or predictions.
A type of model made of layers of connected "neurons" that pass signals to each other, loosely inspired by the human brain.