—
Backpropagation for a multilayer perceptron
Tutor me on https://mlprep.iwase.dev/item/pml-book1-ex13.1/. This is a practice item. If window.mlPrepAgent is available, read attempts for item pml-book1-ex13.1 before tutoring. Inspect my attempt, keep the item ID, and do not reveal the full answer first. After a real attempt, append its record with recorded_by agent, include agent_session_id when available, and read it back.Derives layer errors, parameter gradients, and the input gradient for a one-hidden-layer classifier.
Source caveat
A full-page figure separates the title from the task; the public solution manual predates the dated book draft.
Previous attempts
Loading attempts saved in this browser…