Forward pass and backpropagation

Tutor me on https://mlprep.iwase.dev/item/original-ml-forward-backprop/. If window.mlPrepAgent is available, read attempts for item original-ml-forward-backprop 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.

Problem

A scalar network has $h=\operatorname{ReLU}(wx)$ , $\hat{y}=vh$ , and loss

$L=\frac{1}{2}(\hat{y}-y)^2.$

At $x=2$ , $w=1$ , $v=3$ , and $y=4$ , compute $h$ , $\hat{y}$ , $L$ , $\frac{\partial L}{\partial v}$ , and $\frac{\partial L}{\partial w}$ .

Reveal answer or reference solution

$h=2$ , $\hat{y}=6$ , and $L=2$ . The derivatives are

$\frac{\partial L}{\partial v}=(6-4)h=4$

and

$\frac{\partial L}{\partial w}=(6-4)vx=12,$

because the ReLU input is positive.

Local history

Loading attempts saved in this browser…

Appears in

Machine Learning Diagnostic
Neural Networks Practice