Deep Learning Convolutional Neural Networks

Question 1

What is the primary advantage of convolutional layers over fully connected layers for image data?

Accepted Answer

Parameter sharing and local connectivity reducing parameter count

Answer

Faster training on CPUs

Answer

Larger receptive fields per layer

Answer

Elimination of activation functions

Question 2

What does a convolutional filter (kernel) do when applied to an input feature map?

Accepted Answer

Computes a dot product between the filter and a local patch of the input

Answer

Performs element-wise addition

Answer

Averages all pixel values globally

Answer

Transposes the input matrix

Question 3

What is the purpose of pooling layers in a CNN?

Accepted Answer

Downsample feature maps to reduce computation and add spatial invariance

Answer

Increase spatial resolution

Answer

Apply non-linear activations

Answer

Normalize feature map values

Question 4

What does 'stride' refer to in a convolutional layer?

Accepted Answer

The number of steps the filter moves per application

Answer

The size of the convolutional filter

Answer

The number of output channels

Answer

The padding added to input borders

Question 5

Which famous CNN architecture introduced residual (skip) connections to enable training of very deep networks?

Accepted Answer

ResNet

Answer

AlexNet

Answer

VGGNet

Answer

Inception

Question 6

What is the receptive field of a neuron in a CNN?

Accepted Answer

The region of the input image that influences that neuron's activation

Answer

The set of all neurons in the same layer

Answer

The number of filters in the layer

Answer

The spatial size of the output feature map