CNN Architecture Fundamentals 5

Question 1

What is the primary advantage of using depthwise convolutions over standard convolutions in terms of computational cost?

Accepted Answer

They reduce multiply-add operations by separating spatial and channel-wise filtering

Answer

Depthwise convolutions apply one filter per input channel independently, reducing the number of multiply-add operations by a factor roughly equal to the number of output channels.

Question 2

In the context of CNNs, what does 'weight sharing' mean and why is it important?

Accepted Answer

The same filter weights are applied at every spatial location, drastically reducing parameters

Answer

Weight sharing means one learned filter slides across the entire input, so a layer with a 3×3 filter has only 9 weights per channel regardless of input size.

Question 3

Which architecture introduced the concept of 'network-in-network' using micro neural networks at each convolutional step?

Accepted Answer

Network-in-Network (NIN)

Answer

NIN replaced standard convolutional filters with small multi-layer perceptrons (mlpconv layers) at each location, enabling more complex feature extraction per patch.

Question 4

What is the effect of using a very large learning rate when training a CNN with batch normalization?

Accepted Answer

It can be tolerated better than without BN because BN stabilizes the distribution of layer inputs

Answer

Batch Normalization reduces sensitivity to learning rate by normalizing activations, allowing higher rates that would cause instability in unnormalized networks.

Question 5

In EfficientNet, what is 'compound scaling' and what does it scale jointly?

Accepted Answer

Jointly scaling network width, depth, and input resolution using a fixed ratio

Answer

EfficientNet's compound scaling coefficient φ uniformly scales width (channels), depth (layers), and resolution (input size) with empirically derived ratios.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Architecture Fundamentals 5