Embeddings & Semantic Search

Your phone's autocomplete knows "cat" and "kitten" are related but "cat" and "car" aren't, even though "cat" and "car" share more letters. How? It doesn't read letters. It reads numbers. The word "cat" becomes something like [4, 1] and the machine compares tho

8 lessons, each with runnable code in the browser.

1. Words as Coordinates
2. Cosine Similarity
3. Normalize Once, Compare Fast
4. Build the Movie Recommender
5. Real Embeddings & Semantic Search
6. Embedding Dimensions: What They Capture
7. Chunking Before Embedding
8. Caching and Updating Embeddings

Compilearn home