CNN Architecture Fundamentals 3

Question 1

In VGGNet, what architectural choice was a key design principle?

Accepted Answer

Stacking many small 3×3 convolutional filters instead of large kernels

Answer

VGGNet demonstrated that deep networks using only 3×3 convolutions can achieve strong performance, as two 3×3 layers have the same receptive field as one 5×5 layer with fewer parameters.

Question 2

What problem do residual connections in ResNet primarily solve?

Accepted Answer

Vanishing gradients that hinder training of very deep networks

Answer

Residual (skip) connections allow gradients to flow directly through the network, mitigating vanishing gradient problems that arise in very deep architectures.

Question 3

What is the output size formula for a convolutional layer given input W, filter F, padding P, and stride S?

Accepted Answer

(W + 2P - F) / S + 1

Answer

The spatial output size is computed as (W + 2P − F) / S + 1, which accounts for padding, filter size, and the step size.

Question 4

In the Inception module (GoogLeNet), why are convolutions of different kernel sizes applied in parallel?

Accepted Answer

To capture features at multiple scales simultaneously within the same layer

Answer

Parallel branches with 1×1, 3×3, and 5×5 filters let the Inception module learn features at multiple spatial scales and concatenate them along the depth axis.

Question 5

What is global average pooling (GAP) and why is it used before the final classifier in modern CNNs?

Accepted Answer

It averages across spatial dimensions to produce a single value per feature map, replacing dense layers

Answer

GAP collapses each feature map to a scalar by averaging all spatial values, drastically reducing parameters and providing some translation invariance.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Architecture Fundamentals 3