CNN Overfitting and Regularization 3

Question 1

In a CNN, early stopping halts training when which condition is met?

Accepted Answer

Validation loss stops improving or starts increasing

Answer

Early stopping monitors validation loss and terminates training when it plateaus or increases, indicating the model is beginning to overfit.

Question 2

How does max pooling contribute to a CNN's resistance to overfitting?

Accepted Answer

It reduces spatial resolution, decreasing parameter count in subsequent layers

Answer

Max pooling downsamples feature maps, which reduces the number of inputs to subsequent layers and thus the total number of learned parameters.

Question 3

Which statement about Dropout during inference (test time) in a CNN is correct?

Accepted Answer

Dropout is disabled and weights are scaled by the keep probability

Answer

At inference, Dropout is turned off and weights are scaled by the keep probability (or equivalently, outputs are scaled at training) to maintain expected activation magnitudes.

Question 4

What is the 'bias-variance tradeoff' as it applies to CNN design?

Accepted Answer

Increasing model capacity reduces bias but can increase variance (overfitting)

Answer

Larger CNN capacity reduces training error (bias) but increases sensitivity to training data fluctuations (variance), risking overfitting.

Question 5

CutOut augmentation reduces CNN overfitting by which mechanism?

Accepted Answer

Randomly masking out rectangular regions of training images

Answer

CutOut randomly removes square patches from training images, forcing the CNN to use multiple regions rather than relying on any single discriminative area.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Overfitting and Regularization 3