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

Convolutional layers reuse the same filter weights across spatial positions, drastically reducing parameters while preserving spatial structure.

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

A convolution filter slides over the input and computes the dot product between its weights and each local receptive field, producing an activation map.

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

Pooling layers reduce spatial dimensions by aggregating values in local regions, decreasing computation and making the representation more invariant to small translations.

Question 4

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

Accepted Answer

The number of steps the filter moves per application

Answer

Stride controls how many pixels the filter shifts between consecutive applications, with larger strides producing smaller output feature maps.

Question 5

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

Accepted Answer

ResNet

Answer

ResNet introduced shortcut connections that add the input directly to the output of a block, enabling gradients to flow unimpeded through hundreds of layers.

Deep Learning Practice Test

Deep Learning Practice Test

Deep Learning Convolutional Neural Networks