AI-ML Super Important and Important Questions-18CS71

By TIE Review team-GAT, RNSIT, KSIT, JSSATE, RRCE, BNMIT

Module-1

1. What is a state-space search? Write an algorithm and explain the water Jug problem as a
state-space search
2. What do you mean by heuristic search? Write a heuristic function for travelling salesman
problems?
3. Explain Breadth-first search and depth-first search. List down the advantages and
disadvantages of both?
4. Explain(usual definitions): Production system and characteristics (with def), Problem
characteristics(with def), AI techniques (define AI), Turing test, Control strategy, Hill Climbing
and its adv
5. Explain A* and AO* Algorithm with example
6. Discuss the tic-tac-toe problem in detail and explain how it can be solved using AI techniques

Module-2

1. Explain the different approaches used for knowledge representation and also the qualities
that a good knowledge system should possess
2. Explain Find S algorithm- its properties, drawbacks
3. Explain the candidate elimination algorithm with an example
4. Explain the concept of Inductive bias wrt Candidate elimination algorithm
5. Diff between
(i)Training data and testing data
(ii)Supervised, unsupervised and reinforcement learning
(iii)Inductive biased hypothesis space and unbiased learner
6. Define concept learning, explain a concept learning task(take water sport ex)

Module-3

1. Define decision tree learning and its representation with example? List and explain
appropriate problems for decision tree learning?
2. Explain appropriate problems for Neural networks with their characteristics, List the properties
of Neural Networks?
3. Describe the ID3 algorithm for decision tree learning
4. Write a short note on (i)Perception training rule (ii)Gradient Descent and delta rule
5. Explain Gradient descent and stochastic Gradient descent and their diff
6. Issues in decision tree learning
7. Explain Backpropagation Algorithm with example

Module-4
1. Explain the Naïve Bayes classifier and briefly explain Bayesian belief networks(with example)

2. Derive an equation for MAP hypothesis using Bayes Theorem.

3. Explain the Brute Force MAP learning algorithm and write a short note about
EM Algorithm*
4. Prove that a maximum likelihood hypothesis can be used to predict probabilities and also
explain how it can be used to minimize the squared error between the actual output
hypothesis and the predicted output hypothesis (max likelihood hypo for predicting
probabilities)
5. Describe the Minimum Description length principle in brief with equation
6. The following table gives data set about stolen vehicles. Using Naïve Bayes classifier
classifies the new data (Red, SUV, Domestic) 8M(Jan’19) 6M (Jan/Feb’21)
Colour Type Origin Stolen

Red Sports Domestic Yes

Red Sports Domestic No

Red Sports Domestic Yes

Yellow Sports Domestic No

Yellow Sports Imported Yes

Yellow SUV Imported No

Yellow SUV Imported Yes

Yellow SUV Domestic No

Red SUV Imported No

Red Sports Imported Yes

Module-5

1. Explain locally weighted regression in detail

2. Explain Radial basis functions in detail
3. Explain Q learning and Q function algorithm
4. KNN Algo in detail
5. Explain the Learning task with an example
6. Explain Reinforcement learning problem, With characteristics

Note: These questions are picked by referring to IA papers from 25 Colleges, Diff question banks,
TIE proprietary Model question papers, Questions provided to us by senior teachers under TIE.
We advise you to prepare all the questions from this QB as these are the most probable questions