Core Concepts
Deep Learning
Deep learning uses multi-layer neural networks (deep neural networks) to learn hierarchical representations from data. Each layer extracts progressively more abstract features—from edges to shapes to objects in computer vision, or from characters to words to meaning in NLP.
Deep learning has driven breakthroughs in image recognition, speech synthesis, machine translation, and generative AI. GPUs enabled the scale of computation required, and large labeled datasets provided the training signal.
Authority Links
Related Terms
Model Components
Neural Network
Computational system of interconnected nodes inspired by the human brain that learns to recognize patterns.
Core Concepts
Machine Learning
Getting computers to learn from data and improve at tasks without explicit programming.
Techniques & Methods
Backpropagation
Training algorithm that adjusts neural network weights by propagating prediction errors backward through the network.
Model Components
Transformer
A neural-network architecture, introduced by Vaswani et al. in 2017, that uses self-attention and parallel computation across all sequence positions — the foundation under virtually every frontier language and multimodal model in production today.