Naive Bayes Classification Concepts

What type of machine learning algorithm is Naive Bayes Classification?

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• Semi-supervised learning

What is the main goal of classification in machine learning?

• To group similar data points together without prior labels.

• To predict a continuous output value based on input features.

• To assign data points to predefined categories or classes.

• To discover hidden patterns in unlabeled data.

On which mathematical principle is Naive Bayes Classification primarily based?

• Linear Regression

• Decision Trees

• Bayes' Theorem

• Support Vector Machines

In Naive Bayes Classification, what does the term "Naive" signify regarding the variables used?

• The variables are complex and difficult to understand.

• The variables are assumed to be dependent on each other.

• The variables are assumed to be independent of each other.

• The algorithm is simple and does not require many variables.

As explained in the video, what type of probability does Bayes' Theorem primarily deal with?

• Joint probability

• Marginal probability

• Conditional probability (specifically "reverse" or "cause" probability)

• Unconditional probability

In Naive Bayes classification, why can the denominator P(X) often be disregarded when comparing probabilities for different classes?

• It is always equal to 1.

• It is a constant across all class calculations.

• It represents the prior probability of the features.

• It is only used for normalization, not classification.

What is the fundamental assumption of the Naive Bayes classifier?

• Features are dependent on each other.

• Features are conditionally independent given the class.

• All features have equal importance.

• The prior probability of all classes is equal.

Based on the provided data, what is the prior probability of a person having fever (P(fever = yes))?

• 3/10

• 4/7

• 7/10

• 2/3

Using the provided data, what is the conditional probability of a person having COVID given that they have fever (P(COVID=Yes | Fever=Yes))?

• 3/7

• 4/7

• 2/3

• 7/10

If a new person presents with both Flu and COVID, and the calculated probability of 'Fever Yes' is 0.17 while 'Fever No' is 0.13, what would be the Naive Bayes classifier's prediction for this person's fever status?

• Fever Yes

• Fever No

• Cannot be determined without more data.

• Equally likely to be Fever Yes or Fever No.