Embeddings
From the book I Am Datapedia!, published here free by the author.
Part of I Am Datapedia!
Questions 1–10 of 10
1. What are embeddings?
2. In the context of embeddings, what is a vector?
3. Which pair of words is given as an example of embeddings that would be close to each other in vector space?
4. In data architecture, where are embeddings often stored so that similarity search can be performed?
5. How does an embedding-based search differ from a traditional keyword search when a user searches for 'cheap running shoes'?
6. In the Grade 7 animal example of embeddings, why are dog and wolf considered similar?
7. Conceptually, what does each dimension of an embedding's multi-dimensional space capture?
8. Which of the following is NOT listed as a use of embeddings?
9. What does an image embedding capture, compared with an audio embedding?
10. How do embeddings enable AI systems to combine text and image understanding?