CNN Overfitting and Regularization 4

Question 1

In the context of CNNs, what does 'DropBlock' improve upon compared to standard Dropout?

Accepted Answer

It drops contiguous blocks of spatial units, preventing nearby units from compensating for dropped ones

Answer

DropBlock removes contiguous regions of feature maps so that semantic information in those regions is completely lost, making regularization more effective for CNNs.

Question 2

Which regularization strategy is most directly analogous to Bayesian model averaging for neural networks?

Accepted Answer

Dropout at test time using MC sampling

Answer

Using Dropout with multiple stochastic forward passes at test time (MC Dropout) approximates Bayesian model averaging over an ensemble of models.

Question 3

When applying transfer learning to a pretrained CNN on a small target dataset, which approach BEST reduces overfitting?

Accepted Answer

Freeze early convolutional layers and fine-tune only the top layers

Answer

Freezing pretrained low-level filters preserves generic features and limits trainable parameters to reduce overfitting on the small dataset.

Question 4

How does increasing the batch size during CNN training affect regularization behavior?

Accepted Answer

Smaller batches produce noisier gradient estimates that act as implicit regularization

Answer

Smaller mini-batches introduce gradient noise that acts as implicit regularization, often leading to better generalization.

Question 5

A CNN's training curve shows decreasing training loss but a validation loss that oscillates without clear improvement. What does this indicate?

Accepted Answer

The model is overfitting and the validation set may have high variance

Answer

Decreasing training loss alongside flat or oscillating validation loss is a sign of overfitting, possibly compounded by a small or noisy validation set.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Overfitting and Regularization 4