SEARCH · ENGLISH EDITION
Find an AI concept.
Search titles, summaries, article text, source-language titles, and known aliases.
Attention
A mechanism that lets a neural network weigh the relevance of different positions when computing a representation.
BERT
Bidirectional Encoder Representations from Transformers, an encoder-based language representation model.
Embedding
A numerical vector representation used to encode semantic or structural properties of data.
Foundation Model
A broadly trained model that can be adapted to many downstream tasks and applications.
Google DeepMind
Google's AI research organization, formed from the combination of DeepMind and Google Brain teams.
Knowledge Distillation
A training method in which a smaller student model learns from the outputs or representations of a larger teacher model.
Transformer
A neural network architecture that processes sequences primarily through attention mechanisms.