MS-DS Master of Data science Deep Learning and Neural Networks 3

Question 1

Which deep learning architecture is best suited for sequential text classification tasks due to its ability to process inputs in order?

Accepted Answer

LSTM

Answer

LSTMs maintain a cell state across timesteps, making them well-suited for sequential data where context from earlier inputs affects later predictions.

Question 2

What is the 'vanishing gradient' problem in deep neural networks?

Accepted Answer

Gradients shrinking exponentially as they propagate back through many layers

Answer

In deep networks, repeated multiplication of small gradient values during backpropagation causes them to shrink toward zero, preventing early layers from learning.

Question 3

Which technique involves training a neural network on augmented versions of training data (flips, crops, rotations) to improve generalization?

Accepted Answer

Data augmentation

Answer

Data augmentation artificially expands the training set by applying label-preserving transformations, reducing overfitting and improving model robustness.

Question 4

In deep learning, what does a residual (skip) connection accomplish in architectures like ResNet?

Accepted Answer

Allows gradients to flow directly through skip paths, easing optimization of very deep networks

Answer

Skip connections bypass one or more layers, adding the input directly to the output, which preserves gradient flow and enables training of networks hundreds of layers deep.

Question 5

What is the purpose of the softmax function in the output layer of a neural network for classification?

Accepted Answer

Convert raw logits into a probability distribution that sums to 1

Answer

Softmax exponentiates each logit and divides by the sum of all exponentiated logits, producing a valid probability distribution over class labels.

MS-DS Master of Data science Practice Test

MS-DS Master of Data science Practice Test

MS-DS Master of Data science Deep Learning and Neural Networks 3