From Embeddings to Transformers: The Mathematics of Recommender Systems Through Inner Products
kogo14905334
Free
Intermediate / attention-model, factorization, iframes, recommender-systems, transformer
New
New
Through the single problem of predicting movie ratings, this connects PCA, SVD, matrix factorization, and attention from the perspective of inner products. People who have only called libraries will be able to explain the meaning of embedding numbers and how transformers compute things on their own. It is a journey toward understanding, in a single formula, the entire process of filling in the blanks in a recommender system.
Intermediate
attention-model, factorization, iframes









