Neural Network Convolutional Neural Networks 2

Question 1

What is depthwise separable convolution and what is its main advantage?

Accepted Answer

A factored convolution applied depthwise then pointwise, dramatically reducing parameters and computation

Answer

Depthwise separable convolution applies a single filter per input channel (depthwise) then combines channels with 1×1 convolution (pointwise), drastically reducing computation vs standard convolution.

Question 2

What is feature map visualization and why is it used in CNN analysis?

Accepted Answer

Displaying the intermediate activations to understand what features each layer detects

Answer

Feature map visualization displays the activations of intermediate layers, revealing what patterns (edges, textures, shapes) the network has learned to detect at each stage.

Question 3

What is transfer learning in the context of CNNs?

Accepted Answer

Reusing pretrained CNN weights as a starting point for a new task

Answer

Transfer learning uses a CNN pretrained on a large dataset (like ImageNet) as the starting point for a new task, leveraging learned feature representations to reduce training time and data requirements.

Question 4

In CNN-based image classification, what does the global average pooling layer do before the final classifier?

Accepted Answer

Averages each entire feature map to a single value, reducing spatial dimensions to 1×1

Answer

Global average pooling computes the mean of each feature map, converting spatial feature maps of any size into a fixed-length vector suitable for classification.

Question 5

What does data augmentation accomplish during CNN training?

Accepted Answer

It artificially expands the training set by applying random transformations to existing samples

Answer

Data augmentation applies random transforms (flips, crops, rotations, color jitter) to training images, artificially increasing dataset diversity and reducing overfitting.

Neural Network Practice Test

Neural Network Practice Test

Neural Network Convolutional Neural Networks 2