Skip to content
ml-recall

#weight-sharing

3 questions from Neural Network Basics, Recurrent Neural Networks, Graph Neural Networks

Timed test

3 questions · 3 min · score and explanations at the end

Take a test
Q 1 / 3Score 0 / 0

Question 1: Single choice

hardAI-checkedNeural Network Basics

A weight matrix W∈Rd×dW \in \mathbb{R}^{d \times d} is used twice: y=Wx,u=ReLU(y),v=u+Wu,L=12∥v∥22.y = Wx,\quad u = \mathrm{ReLU}(y),\quad v = u + Wu,\quad L = \tfrac12 \lVert v \rVert_2^2. With Θ\Theta the elementwise step function (Θ(yk)=1\Theta(y_k) = 1 if yk≥0y_k \ge 0, else 0), which expression is ∂L/∂W\partial L / \partial W?

Choose one option