ML Quiz

What is a feature importance score?

• A measure of feature correlation

• A measure of feature variability

• A measure of how useful a feature is in predicting the target variable

• None of the rest

What is the purpose of regularization in feature selection?

• To handle missing values

• To prevent overfitting by adding a penalty to the model

• To reduce the size of the dataset

• All of them are correct

What is backward elimination in feature selection?

• A method that starts with no features and adds the most significant ones

• A method that scales features

• A method that starts with all features and removes the least significant ones

• A method that eliminates random features

What is the difference between feature selection and feature extraction?

• They are the same process

• Feature selection creates new features; feature extraction removes features

• Feature selection selects existing features; feature extraction creates new features

• No of these are correct

What is variance thresholding?

• A technique to scale features

• A technique to handle missing values

• A feature selection technique that removes features with low variance

• All of them are correct

Which of the following is a reasonable way to select the number of principal components k?

(Recall that n is the dimensionality of the input data and m is the number of input examples.)

• • Choose k to be the smallest value so that at least 99% of the variance is retained.  

• • Choose k to be 99% of m (i.e., k = 0.99 * m, rounded to the nearest integer).  

• • Choose k to be the largest value so that at least 99% of the variance is retained

• • Use the elbow method.

Naïve Bayes algorithm is based on ______ and used for solving classification problems

• Bayes Theorem
• Candidate elimination algorithm
• EM algorithm
• Nove of these

How do we perform bayesian classification when some features are missing ?

• We assume the missing values as the mean of all values
• We ignore the missing features
• We integrate the posteriors probalities over the missing features
• Drop the features completely

which is suitable metric for categoricl variable to find similarity ?

• Euclidiean distance
• Manhattan distance
• Minkowski distance
• Hamming distance

Wchih is a dicission support tool that uses a tree-like graph Or model of decission and their possible consequences including chance event outcomes, resources cost, and utility ?

• Decision Tree
• Graphs
• Trees
• Neural Networks