Deep Learning Neural Network Fundamentals 3

Question 1

What is the softmax function used for in neural networks?

Accepted Answer

Converting raw scores into a probability distribution over classes

Answer

Softmax converts a vector of raw logits into probabilities that sum to 1, making it suitable for multi-class classification output layers.

Question 2

What problem does batch normalization primarily address?

Accepted Answer

Internal covariate shift causing unstable training

Answer

Batch normalization reduces internal covariate shift by normalizing layer inputs to have zero mean and unit variance, stabilizing and accelerating training.

Question 3

In a neural network, what is an epoch?

Accepted Answer

One complete pass through the entire training dataset

Answer

An epoch represents one full pass through all training samples, after which the model has seen every example once.

Question 4

Which technique randomly sets neuron outputs to zero during training to reduce overfitting?

Accepted Answer

Dropout

Answer

Dropout randomly deactivates a fraction of neurons during each training step, preventing co-adaptation and acting as an ensemble of sub-networks.

Question 5

What is the difference between stochastic gradient descent (SGD) and mini-batch gradient descent?

Accepted Answer

SGD updates weights using one sample; mini-batch uses a small subset

Answer

SGD computes the gradient from a single training example per update, while mini-batch gradient descent averages gradients over a small batch of examples.

Deep Learning Practice Test

Deep Learning Practice Test

Deep Learning Neural Network Fundamentals 3