Backpropagation and the Training Loop

3 min
Audience
ages 10–15
Duration
30 to 40 min
Adventure
3/8
Badge to earn
Loop Chief

Today's mission

Order a full loop: batch, prediction, loss, gradients, update, then repeat.

Proof of success: explain "Backpropagation and the training loop", complete "The Round of Six Roles" and name the limit of the analogy.

The story

A team trains a paper network to recognize three made-up geometric flags. At each mini-batch, they compute the outputs, measure the loss, propagate the gradients backward and modify the parameters. The learning rate controls the size of the change. After going through all the cards, one epoch is done. Repeating without measuring validation would be dangerous: the model could memorize the training set by heart.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

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 one
This lesson is part of the “How the Network Learns” module

The 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.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one