The diagram is the lab contract: any consultation of the test before step G invalidates the final measurement. Every arrow must leave a reproducible trace in the report.
Goal: train a first complete network offline with a clean protocol. Duration: 2 to 3 hours. Script:
code/train_mlp_digits.py.
The load_digits dataset contains 1,797 images 8×8 of digits 0 to 9. Build
an MLP, stratify train/validation/test split, choose hyperparameters on
validation and use the test set only once.
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.