Tokenize a made-up sentence, associate vectors and show why closeness doesn't mean perfect synonymy.
Proof of success: explain "Tokens and embeddings", complete "The Vector Dictionary" and name the limit of the analogy.
In the club's imaginary newsletter, the sentence "The fireflies light up the garden" has to become numbers. Maëlle discovers that a tokenizer can separate punctuation, words or word fragments. Each token gets an identifier, then an embedding table turns this identifier into a vector. The vectors are tuned during learning: similar usages can bring some directions closer, but the geometry depends on the corpus and the objective.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.