CNN Architecture Fundamentals 4

Question 1

Which pooling operation is most commonly used in CNNs and what does it compute?

Accepted Answer

Max pooling — selects the maximum value in the pooling window

Answer

Max pooling takes the largest activation within each region, retaining the strongest feature response and providing a degree of translation invariance.

Question 2

In DenseNet, how does each layer receive its input?

Accepted Answer

From all preceding layers via concatenation

Answer

DenseNet concatenates feature maps from all preceding layers as input to each layer, maximizing feature reuse and enabling gradient flow through the entire network.

Question 3

What is the key innovation in MobileNetV2's inverted residual block compared to standard residual blocks?

Accepted Answer

It expands channels before the depthwise convolution, then compresses with a linear bottleneck

Answer

MobileNetV2 inverts the bottleneck by expanding channels first, applying depthwise conv, then projecting back to a low-dimensional space with a linear activation.

Question 4

What does 'dilation' (atrous convolution) add to a standard convolution?

Accepted Answer

Spaces between filter elements, enlarging the receptive field without increasing parameters

Answer

Dilated convolution inserts gaps (holes) between filter weights, exponentially growing the receptive field while keeping the parameter count and resolution constant.

Question 5

In a fully convolutional network (FCN), what replaces the fully connected layers to enable pixel-wise predictions?

Accepted Answer

Transposed convolutions (or bilinear upsampling) to recover spatial resolution

Answer

FCNs replace dense layers with convolutional ones and use transposed convolutions to upsample feature maps back to the input resolution for dense prediction.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Architecture Fundamentals 4