A technique that normalizes activations across the features of each training example, rather than across the batch.
A technique that normalizes activations across the features of each training example, rather than across the batch. More stable than batch normalization for transformers and recurrent networks because it doesn't depend on batch size. Standard in modern transformer architectures.
A technique that normalizes the inputs to each layer in a neural network, making training faster and more stable.
The neural network architecture behind virtually all modern AI language models.
The process of teaching an AI model by exposing it to data and adjusting its parameters to minimize errors.
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.
Browse our complete glossary or subscribe to our newsletter for the latest AI news and insights.