CS 451 Quiz 33
Convolutional nets
Email address *
In a convolutional layer, the weights in the convolution filters play a similar role as the weight matrix W in a fully-connected layer *
Given a 6x6x3 input image, what is the shape of the output of a convolutional layer that applies 5 filters of shape 3x3x3? *
Unlike in a fully-connected layer, in a convolutional layer we don't have any bias parameters *
What types of layers does a convolutional net typically contain? Check all that apply *
Given the matrix [1 2 3; 4 5 6; 7 8 9], what is the output of a max-pooling layer with filter size f=2 and stride s=1? *
A pooling layer has no parameters that need to be learned *
If you start from the input layer and go from layer to layer deeper into a CNN, what typically happens? *
What is a typical sequence of layers? *
Which layers have the most parameters, which the least? Order from most (left) to least (right) *
Which of the following does NOT explain why convolutions are a good idea? *
This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Additional Terms