AI & Machine Learning Convolutional Neural Networks (CNNs) Quiz

This quiz is about convolutional neural networks, the models behind most computer vision. You will calculate output shapes with the size formula, count a conv layer's parameters and explain why CNNs beat dense layers on images.

Medium 10 questions ~6 minutes Pass at 80%

Choose a mode

Playing as a guest: sign in to keep your XP and streak.

Sample question

Question 1 of 10

A 32x32 single-channel image goes through a 3x3 convolution with stride 1 and no padding. What is the output size?

Show the answer

A. 30x30 (W - K + 2P) / S + 1 = (32 - 3 + 0) / 1 + 1 = 30. A 3x3 kernel cannot be centered on the border pixels without padding, so one pixel is lost on each side.

What this quiz covers

  • Output size = floor((W - K + 2P) / S) + 1
  • Parameter counts of a conv layer
  • Max pooling, padding and stride
  • Weight sharing and receptive fields
  • What 1x1 convolutions are for

Questions people ask

Do I need an account?

No. Anyone can play. Sign in to keep your XP, streak, badges and history.

Can I retake it?

Yes. Your best score is kept, and the questions and answers are shuffled each time.