Choose a stopping point using validation and turn errors into investigation categories.
Proof of success: explain "Early stopping and the error investigation", complete "The Wall of Errors" and name the limit of the analogy.
After twelve epochs, the validation loss of Arthur's model hits its minimum at epoch 7 and then rises. Arthur keeps the epoch 7 checkpoint instead of the last one. Next, he lays out the errors: erased strokes, patterns never seen, disputable labels and ambiguous cases. This taxonomy leads to better actions than a single average. Some errors call for new data; others call for correcting the question or abstaining.
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.