Deep Learning (Data Scientist) 2

Question 1

A data scientist notices training loss decreasing while validation loss starts rising after epoch 15. What is the most appropriate response?

Accepted Answer

Apply early stopping or regularization

Answer

Diverging training and validation loss indicates overfitting, which early stopping or regularization directly addresses.

Question 2

Which technique randomly deactivates a fraction of neurons during training to reduce overfitting?

Accepted Answer

Dropout

Answer

Dropout randomly zeroes out neurons during training, forcing the network to learn redundant representations.

Question 3

Why does batch normalization typically allow the use of higher learning rates?

Accepted Answer

It stabilizes the distribution of layer inputs during training

Answer

By normalizing layer inputs, batch normalization smooths the optimization landscape, permitting larger learning rates without divergence.

Question 4

A model for credit risk uses a sigmoid output. The predicted probabilities cluster near 0.5 despite clear class separation in the data. Which is the most likely cause?

Accepted Answer

The model is underfitting due to insufficient capacity or training

Answer

Predictions stuck near 0.5 on separable data signal underfitting, since a well-trained model would push probabilities toward the extremes.

Question 5

Which loss function is most appropriate for a multi-class classification network with a softmax output layer?

Accepted Answer

Categorical cross-entropy

Answer

Categorical cross-entropy directly measures the divergence between the softmax probability distribution and the one-hot target.

Deep Learning Practice Test

Deep Learning Practice Test

Deep Learning (Data Scientist) 2