Question 1

Which of the following is the definition of accuracy?

Options :

A : (True Positives + False Positives) / Total Predictions

B : (True Positives + True Negatives) / Total Predictions

C : True Positives / (True Positives + False Negatives)

D : True Positives / (True Positives + False Positives)

Answer: B

Question 2

Which of the following options is a correct approach for scheduling model retraining in a weather prediction application?

Options :

A : As new resources become available

B : Once a month

C : When the input format changes

D : When the input volume changes

Answer: C

Question 3

Which of the following best describes distributed artificial intelligence?

Options :

A : It does not require hyperparemeter tuning because the distributed nature accounts for the bias.

B : It intelligently pre-distributes the weight of starting a neural network.

C : It relies on a distributed system that performs robust computations across a network of unreliable nodes.

D : It uses a centralized system to speak to decentralized nodes.

Answer: C

Question 4

Word Embedding describes a task in natural language processing (NLP) where:

Options :

A : Words are converted into numerical vectors.

B : Words are featurized by taking a histogram of letter counts.

C : Words are featurized by taking a matrix of bigram counts.

D : Words are grouped together into clusters and then represented by word cluster membership.

Answer: A

Question 5

Which of the following is NOT a valid cross-validation method?

Options :

A : Bootstrapping

B : K-fold

C : Leave-one-out

D : Stratification

Answer: D