Jawaharlal Nehru Technological University Hyderabad
Jawaharlal Nehru Technological University Hyderabad MCA 2019 MACHINE LEARNING Previous Question Paper (April/May - 2019 - R17)
Note: This question paper contains two parts A and B. Part A is compulsory which carries 25 marks. Answer all questions in Part A. Part B consists of 5 Units. Answer any one full question from each unit.
PART - A
Define Inductive bias.
Answer
Inductive bias refers to the set of assumptions that a learning algorithm uses to predict outputs for inputs that it has not encountered during training. Since a learner must generalize beyond its training data, it requires these assumptions to choose between multiple hypotheses that are consistent with the observed data. Without an inductive bias, the learner cannot prefer one consistent hypothesis over another, making generalization impossible.
Define: i) Sample error ii) True error
Answer
i) Sample error: The fraction of errors made by a hypothesis on the specific set of training data provided to the learner.
ii) True error: The probability that a hypothesis will misclassify an instance drawn randomly from the entire underlying distribution of the data.
Explain minimum description length principle.
Answer
Sign in to view the complete answer paper.
Explain briefly codebook generation.
Answer
Sign in to view the complete answer paper.
Explain using prior knowledge to alter the search objective.
Answer
Sign in to view the complete answer paper.
PART - B
Hand trace the Candidate – Elimination algorithm on the training data provided in the curriculum.
Answer
Sign in to view the complete answer paper.
Write the Candidate-Elimination Algorithm.
Answer
Sign in to view the complete answer paper.
Write the relevant Mathematical formulae and describe the working of Perceptron with a neat diagram. Hand trace the perceptron learning rule to implement 2 input EX-OR gate for 2 iterations through all 4 training examples.
Answer
Sign in to view the complete answer paper.
Explain basics of sampling theory.
Answer
Sign in to view the complete answer paper.
Explain Error estimation and estimating Binomial Proportions.
Answer
Sign in to view the complete answer paper.
Explain the working of Naïve Bayes classifier with necessary formulae and with an example.
Answer
Sign in to view the complete answer paper.
Explain the working of Bayes optimal classifier with an example.
Answer
Sign in to view the complete answer paper.
Explain Maximum Description Length principle.
Answer
Sign in to view the complete answer paper.
Explain Discrete Markov Processes.
Answer
Sign in to view the complete answer paper.
Explain the working of HMMs.
Answer
Sign in to view the complete answer paper.
Explain Inductive and analytical learning problems with examples.
Answer
Sign in to view the complete answer paper.
Write the explanation based learning algorithm: Prolog-EBG.
Answer
Sign in to view the complete answer paper.
Write and explain KBANN algorithm.
Answer
Sign in to view the complete answer paper.