Skip to content
ml-recall

#fully-connected

2 questions from Convolutional Neural Networks, Landmark Architectures

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

mediumAI-checkedConvolutional Neural Networks

A 32×3232 \times 32 RGB image (3,072 input values) must be mapped to a 32×32×1632 \times 32 \times 16 feature map. A 3×33 \times 3 convolution with padding 1 and 16 output channels needs 3⋅3⋅3⋅16+16=4483\cdot3\cdot3\cdot16 + 16 = 448 parameters. How many parameters (weights plus biases) does a fully connected layer with the same input and output sizes need?

a whole number