ML2 PDF Bayes

What is the Naive Bayes method?

• A method for calculating marginal probability

• A method for calculating joint probability

• A method for calculating conditional probability

• A method for calculating prior probability

Why is Naive Bayes called 'naive'?

• Because it calculates posterior probability

• Because it considers all possible hypotheses

• Because it uses complex Bayesian methods

• Because it assumes independence between predictor variables

What is the key concept of posterior probability P(H|e)?

• The probability of the evidence under all possible hypotheses

• The probability of the hypothesis before knowing about the evidence

• The probability of observing predictor values given an outcome

• The class to which the observation belongs given the set of evidence

What is the basis of Naive Bayes algorithm?

• Log probabilities

• Laplace smoothing

• Maximum a posteriori probability

• Bayes rule

What is the purpose of Laplace smoothing in Naive Bayes?

• To solve the problem of zero probability

• To convert products into sums

• To calculate log-odds instead of probabilities

• To avoid overfitting

When to use Naive Bayes algorithm?

• When dealing with irrelevant features

• As an initial algorithm for initial predictions

• When in need of something slow and complex

• As a final algorithm for accurate predictions

What is the memory requirement for Naive Bayes algorithm?

• Depends on the dataset

• Medium

• Large

• Small

What is the difficulty level of Naive Bayes algorithm?

• Small

• Depends on the Dataset

• Medium

• High

What is the training time for Naive Bayes algorithm?

• Medium

• Depends on the dataset

• Large

• Small