Dot product
Dot product: The sum of products between corresponding vector components, related to angle, norms and projections. It is zero for non-zero orthogonal vectors. For normalised embeddings it equals cosine similarity and accelerates many retrieval calculations. This perspective connects the definition with practical behaviour in artificial intelligence systems.
In italiano: Prodotto ScalareLegge I · Embedding, feature e spazi vettorialiIt is zero for non-zero orthogonal vectors. For normalised embeddings it equals cosine similarity and accelerates many retrieval calculations.