ML Test2 Set 1 QP
ML Test2 Set 1 QP
ML Test2 Set 1 QP
PART-A
Total 5 Marks (No choice)( CO2, BL-4)
SN Question Marks
1a Differentiate between the True error and the Sample error, write the corresponding equations of 5
the same
PART-B
Total 15 Marks (No Choice) (CO1, BL-3)
SN Questions Marks
2a What is the probability that a woman has cancer if she has a positive mammogram result? 5
Given the following statistics are:
• One percent of women over 50 have breast cancer
• Ninety percent of women who have breast cancer test positive on mammograms
• Eight percent of women will have false positives
2b Suppose you test a hypothesis h and find that it commits r = 12 errors on a sample S of n = 40 5
randomly drawn test examples. What is the standard deviation in error s(h)?
2c The standard deviation given is 0.40 and the size of the samples is 2500, find the sampling error 5
at the confidence interval equal to 95%
PART- C
Total 20 marks (Answer any two - 3a or 3b and 4a or 4b)( CO3, BL-5)
SN Question Marks
3a Assume that the learner considers some finite hypothesis space H which is defined over the 10
instance space X [((x1,d1), (x2,d2),…(xm,dm)) where xi is some instance from X and where
di is the target value of xi], in which the task is to learn some target concept C: X {0,1}.
Design a Concept Learning algorithm based on Bayes theorem to output the maximum a
posteriori hypothesis
OR
3b Consider a learned hypothesis, h, for some boolean concept. When h is tested on a set of 100 10
examples, it classifies 85 correctly. What is the standard deviation and the 95% confidence
interval for the true error rate for Error D(h)
4a You can detect spam e-mails in your inbox. Assume that the word ‘offer’ occurs in 80% of 10
the spam messages in your account. Also, let’s assume ‘offer’ occurs in 10% of your desired
e-mails. If 30% of the received e-mails are considered as a spam, and you will receive a new
message which contains ‘offer’. What is the probability that it is spam
OR
4b Suppose Lp and Lq are two learning algorithms. The performance of two learning algorithms 10
is to be compared. Write the steps to compare and discuss the statistical justification for this
procedure