Skip to content
ml-recall

#linear-layers

1 question from Linear Models & Regularization

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedLinear Models & Regularization

Two linear layers are composed without an activation function in between, h=W1x+b1\mathbf{h} = \mathbf{W}_1\mathbf{x} + \mathbf{b}_1 and o=w2⊤h+b2o = \mathbf{w}_2^\top\mathbf{h} + b_2, with

W1=[1201−11],b1=[102],w2=[1−12],b2=0.5.\mathbf{W}_1 = \begin{bmatrix} 1 & 2 \\ 0 & 1 \\ -1 & 1 \end{bmatrix},\quad \mathbf{b}_1 = \begin{bmatrix} 1 \\ 0 \\ 2 \end{bmatrix},\quad \mathbf{w}_2 = \begin{bmatrix} 1 \\ -1 \\ 2 \end{bmatrix},\quad b_2 = 0.5.

The pair computes the single layer o=w⊤x+bo = \mathbf{w}^\top\mathbf{x} + b with w=\mathbf{w} = ( , ) and b=b = .

Fill in every blank (hints in the boxes). Enter moves to the next blank.