Question 1

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 2

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 3

Your dependent variable Y is a count, ranging from 0 to infinity. Because Y is approximately log-normally distributed, you decide to log-transform the data prior to performing a linear regression. What should you do before log-transforming Y?

Options :

A : Add 1 to all of the Y values.

B : Divide all the Y values by the standard deviation of Y.

C : Explore the data for outliers.

D : Subtract the mean of Y from all the Y values.

Answer: A

Question 4

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 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