CNN Overfitting and Regularization 2

Question 1

Which regularization technique randomly zeroes out feature maps during training in CNNs rather than individual neurons?

Accepted Answer

Spatial Dropout

Answer

Spatial Dropout drops entire feature maps (channels) instead of individual activations, which is more effective for spatially correlated CNN features.

Question 2

A CNN trained on 10,000 images achieves 99% training accuracy but only 62% validation accuracy. Which symptom does this describe?

Accepted Answer

Overfitting

Answer

A large gap between training accuracy (99%) and validation accuracy (62%) is the classic symptom of overfitting.

Question 3

What effect does L1 regularization have on CNN weight vectors compared to L2?

Accepted Answer

It produces sparse weights with many zeros

Answer

L1 regularization adds an absolute-value penalty that drives many weights exactly to zero, producing sparse weight vectors.

Question 4

During CNN training, which data augmentation technique generates new training samples by combining two images and their labels linearly?

Accepted Answer

Mixup

Answer

Mixup creates training samples as convex combinations of pairs of training examples and their labels.

Question 5

What is weight decay in the context of CNN optimization, and how does it relate to L2 regularization?

Accepted Answer

It is equivalent to L2 regularization for SGD but differs for Adam

Answer

Weight decay and L2 regularization are equivalent under SGD but diverge under adaptive optimizers like Adam due to interaction with moment estimates.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Overfitting and Regularization 2