Machine Learning Neural Networks 4

Question 1

What is the exploding gradient problem and a common mitigation technique?

Accepted Answer

Gradients growing exponentially; mitigated by gradient clipping

Answer

Exploding gradients occur when backpropagated values grow exponentially; gradient clipping caps gradient norms to keep updates stable.

Question 2

In a CNN, what does 'pooling' accomplish?

Accepted Answer

Reduces spatial dimensions while retaining dominant features

Answer

Pooling (e.g., max pooling) downsamples feature maps by summarizing regions, reducing computation and providing spatial invariance.

Question 3

What is the difference between a shallow and a deep neural network?

Accepted Answer

Deep networks have more hidden layers than shallow networks

Answer

Depth refers to the number of hidden layers; deep networks have many hidden layers enabling hierarchical feature learning.

Question 4

What is the role of an embedding layer in a neural network processing text?

Accepted Answer

It maps discrete tokens to dense continuous vector representations

Answer

An embedding layer learns a dense vector for each token, capturing semantic relationships in a continuous space.

Question 5

Which scenario best describes overfitting in a neural network?

Accepted Answer

Training loss is low but validation loss is much higher

Answer

Overfitting occurs when the model memorizes training data, leading to low training loss but poor generalization on unseen validation data.

Machine Learning Practice Test