MS-DS Master of Data science Deep Learning and Neural Networks 1

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

ReLU (Rectified Linear Unit) avoids vanishing gradients because its gradient is 1 for positive inputs, enabling deeper networks to train effectively.

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

Pooling layers downsample feature maps, reducing spatial size and computational cost while providing a degree of translation invariance.

Question 3

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

Accepted Answer

Gradient clipping

Answer

Gradient clipping caps gradient norms at a threshold, preventing them from growing unbounded during BPTT in RNNs.

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

The forget gate uses a sigmoid function to output values between 0 and 1, determining how much of the previous cell state to retain.

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

Transfer learning leverages a model pre-trained on a large dataset (e.g., ImageNet) and fine-tunes it on a smaller, task-specific dataset.

MS-DS Master of Data science Practice Test