Compare two loss functions and show that choosing a loss means choosing which errors will guide learning.
Proof of success: explain "The loss: defining what matters", complete "Two Referees, Two Rankings" and name the limit of the analogy.
In an imaginary city, Camille predicts the number of bicycles at a station. Two days have errors of 2 and 10 bikes. MAE averages the distances; MSE squares the errors and gives much more weight to the error of 10. No calculation is universally "fair". Before training, the team must link the loss to real consequences and keep readable metrics for evaluation.
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.