Artificial intelligence · University
Embeddings, similarity and retrieval representations · revision notes
An embedding represents an item as a vector learned or designed for a task. Nearby vectors reflect the representation’s notion of similarity, not universal meaning.
Key ideas and conditions
Embedding
An embedding represents an item as a vector learned or designed for a task. Nearby vectors reflect the representation’s notion of similarity, not universal meaning.
Cosine
For nonzero vectors, cosine similarity is u·v/(norm(u)norm(v)). It compares direction and differs from Euclidean distance.
Retrieval
An embedding search retrieves candidates. Relevance, factual correctness and permissions still need additional checks.
Evaluation
Test representations on the intended language, domain and retrieval tasks. A low-dimensional visual projection can distort relationships.
Explain without looking
- Why should multilingual retrieval be evaluated in each intended language?
- For u=(3,4), calculate its Euclidean norm.
Further reading and review references
These are reference links, not copied exercises, institutional endorsement or proof of independent review.
AI-assisted preview; independent educational review required. Level labels describe prerequisites, not accreditation or official curriculum alignment.