Glossary term
Glossary term
Foundations
The d-dimensional vector space that features from a higher-dimensional vector space are mapped to. Embedding space is trained to capture structure that is meaningful for the intended application.
The dot product of two embeddings is a measure of their similarity.
Created for this library
A retail recommendation team places customer and product vectors in a shared embedding space so similarity reflects affinity rather than raw feature overlap.
A search-quality team builds a query and document embedding space so semantically similar queries and documents end up close in that space.
A music platform uses an embedding space where similar songs cluster together so its recommendation system can produce coherent playlists.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License