The most popular deep learning framework, developed by Meta. Used by most AI researchers and many production systems. Known for its intuitive Python-like interface and dynamic computation graphs that make debugging easier. Most new AI papers use PyTorch. Competes with Google's JAX and TensorFlow.
A subset of machine learning that uses neural networks with many layers (hence 'deep') to learn complex patterns from large amounts of data.
Google's open-source deep learning framework.
A mathematical function applied to a neuron's output that introduces non-linearity into the network.
An optimization algorithm that combines the best parts of two other methods — AdaGrad and RMSProp.
Artificial General Intelligence.
The research field focused on making sure AI systems do what humans actually want them to do.
Browse our complete glossary or subscribe to our newsletter for the latest AI news and insights.