Link data type, task, baseline and architecture without picking the most impressive model.
Proof of success: explain "Choosing an architecture and a baseline", complete "The Council of Four Projects" and name the limit of the analogy.
Four teams arrive at Rania's studio: texture grids, sequences of symbols, made-up sentences and tabular measurements. All of them demand a Transformer. Rania starts with the need, the format and a simple measurable rule. She proposes a CNN for grids, a recurrent sequence or a Transformer for text if context justifies it, and an MLP or even a rule for small tables. The budget and the risk can make the baseline win.
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.