NPTEL Learning Analytics Tools Week 9 Assignment Answers 2024
1. A student takes an exam in two subjects. Given that he has passed one of the subjects, what is the probability that he has passed both subjects?
- 0.75
- 0.50
- 0.25
- 0.33
Answer :- For Answers Click Here
2. Which of the following statements about decision trees are correct?
- It requires the normalization of data
- It does not require the normalization of data
- Missing Values are not important
- A decision tree does not need a root node always
Answer :- For Answers Click Here
3. “ The Decision tree is a non-linear classifier.”
- True
- False
Answer :- For Answers Click Here
4. Overfitting and increase in the tree complexity can be overcome through the process called ___________.
- Normalization
- Branching
- Pruning
- Classification
Answer :-
5. Consider the following statements-
A) Naive Bayes assumes independence among predictors.
B) Naive Bayes can perform multi-class prediction.
Which of the following statements is correct?
- Both a and b
- Only a
- Only b
- Neither a nor b
Answer :-
Consider the data provided in the table below and using the Naive Bayes classifier formula, answer the following questions: Q.6 & Q.7
6. What is the probability that a student with 41-60% attendance will pass the exam?
- 2/5
- 4/5
- 3/5
- 1/5
Answer :- For Answers Click Here
7. What is the probability that a 71-80% attendance student will fail the exam?
- 0
- 1/2
- 2/3
- 1/3
Answer :-
Answer the questions 8, and 9 from the information given below:
A researcher is designing a decision tree classifier to classify students based on their exam performance, where scores greater than or equal to 50% are considered a pass, and scores less than 50% are considered a fail. The data is given in the table below:
8. Find the entropy of the target column.
- 0.92
- 0.82
- 0.72
- 0.6
Answer :-
9. Calculate the ‘information gain’ for the parameter ‘Attendance in %’.
- 1
- 0.75
- 0.5
- 0.25
Answer :-
10. Why is the Naive Bayes classifier called ‘Naive’?
- The classifier can solve only a very limited number of problems under multiple conditions
- Its use is limited to the domains of Natural Language Processing and Learning Analytics
- It assumes that the features of input space are strongly independent
- It assumes that the features of input space are strongly dependent.
Answer :- For Answers Click Here
