MS-DS Master of Data science Deep Learning and Neural Networks

Question 1

Which activation function is most commonly used in hidden layers of deep neural networks to mitigate the vanishing gradient problem?

Accepted Answer

ReLU

Answer

Sigmoid

Answer

Tanh

Answer

Softmax

Question 2

In a convolutional neural network (CNN), what is the primary purpose of a pooling layer?

Accepted Answer

Reduce spatial dimensions and computation

Answer

Add non-linearity

Answer

Normalize activations

Answer

Increase filter depth

Question 3

What technique is used in recurrent neural networks (RNNs) to address exploding gradients during backpropagation through time?

Accepted Answer

Gradient clipping

Answer

Dropout regularization

Answer

Batch normalization

Answer

Weight decay

Question 4

Which component of an LSTM cell is responsible for deciding what information to discard from the cell state?

Accepted Answer

Forget gate

Answer

Input gate

Answer

Output gate

Answer

Memory gate

Question 5

In deep learning, what does 'transfer learning' refer to?

Accepted Answer

Using a pre-trained model's weights as the starting point for a new task

Answer

Moving model weights between GPUs

Answer

Transferring data across training epochs

Answer

Copying hyperparameters from one model to another

Question 6

Which loss function is standard for multi-class classification in neural networks?

Accepted Answer

Categorical cross-entropy

Answer

Mean squared error

Answer

Binary cross-entropy

Answer

Huber loss