Foundations
Deep Learning
Machine learning built on large neural networks with many layers, which is what powers most recent AI breakthroughs.
Deep learning uses neural networks stacked into many layers, where each layer learns to spot slightly more abstract features than the one below it. The depth is what lets these models handle messy, high-dimensional data like images, audio, and language without hand-crafted rules. Nearly every headline AI system of the last decade, from image generators to large language models, is a deep learning system.
Reference: Wikipedia: Deep Learning
Related terms
Neural Network
A model loosely inspired by the brain, built from layers of simple units that each pass signals to the next.
Machine Learning
A way of building software that learns patterns from examples instead of being told exactly what to do.
Transformer
The neural network design behind almost every modern language model, built around a mechanism called attention.
Convolutional Neural Network
A network design built for images, which scans for small visual patterns and builds them up into recognizable objects.