1. What is Intelligence?

2. Describe the four categories under which AI is classified with?

3. Define Artificial Intelligence.
4. List the fields that form the basis for AI.
5. What is a Knowledge Based System?
6. List few of the task domains of AI.
7. Give the components of a KBS
8. Describe meta-knowledge?
9. Give the expansion of LISP and PROLOG
10. Interpret the meaning of a Production System.
11. Illustrate the definition of state-space search technique.
12. Show the steps involved in performing a state-space search.
13. Demonstrate the meaning of heuristic search
14. Compare Informed & Uninformed search with examples
15. Analyze the logic behind– Hill climbing, Best-First Search, BFS and DFS.
16. Analyze the meaning of means-end analysis.
17. Deduce the various problem characteristics.
18. Assess when hill climbing fails to find a solution?
19. Formulate the ways to overcome hill climbing problems.
20. Prepare the requirements of a good control strategy.
21. Describe briefly the various problem characteristics?
22. Identify the problems encountered during hill climbing and list the ways available todeal
with these problems?
23. Describe the process of simulated annealing with example?
24. Discuss A* and AO* algorithm and the various observations about algorithmbriefly?
25. Illustrate in detail about the constraint satisfaction procedure with example?
26. Show how the steepest accent hill climbing works?

27. Explain in detail about the mean end analysis procedure with example?
28. Evaluate a problem as a state space search with an example?
29. Prepare the merits and demerits of depth-first and breadth-first search with the
algorithm?
30. Enumerate Classical “Water jug Problem”. Describe the state space for this problem
and also give the solution.
31. How to define a problem as state space search? Discuss it with the help of an example
32. Solve the given problem. Describe the operators involved in it.
i. Consider a Water Jug Problem : You are given two jugs, a 4-gallon one
and a 3-gallon one. Neither has any measuring markers on it. There is a
pump that can be used to fill the jugs with water. How can you get
exactly 2 gallons of water into the 4-gallon jug ? Explicit Assumptions:
A jug can be filled from the pump, water can be poured out of a jug
onto the ground, water can be poured from one jug to another and that
there are no other measuring devices available.
33. Define the following problems. What types of control strategy is used in the
following problem.
a. The Tower of Hanoi
ii.Crypto-arithmetic
i. iii.The Missionaries and cannibals
problems iv.8-puzzle problem
34. Discuss uninformed search methods with examples.
35. Give an example of a problem for which breadth first search would work better
than depth first search.
36. Explain the algorithm for steepest hill climbing
37. Explain the A* search and give the proof of optimality of A*
38. Explain AO* algorithm with a suitable example. State the limitations in the
algorithm?
39. Explain the nature of heuristics with example. What is the effect of heuristics
accuracy?
40. Explain the various types of hill climbing search techniques.
41. Discuss about constraint satisfaction problem with a algorithm for solving a crypt
arithmetic Problem.
42. Solve the following Crypt arithmetic problem using constraints satisfaction search
procedure.
CROSS
+ROADS
=DANGER
43. Explain alpha-beta pruning algorithm and the Minmax game playing algorithm
with example?
 UNIT 2

1. How predicate logic is helpful in knowledge representation.

2. Define semantic networks

3. Identify the need of facts and its representation?

4. Describe property inheritance?

5. Tell briefly about ISA and Instance classes

6. Identify some use of conceptual dependency

7. Discuss FOL with an example

8. Give the definition of Horn clause.

9. Discuss uniqueness quantifier

10. Give the definition of Canonical horn clause

11. Show the difference between propositional and FOL

Logic

12. Analyse the definition of logic

13. Infer the definition of unification

14. Analyse clausal form and its usefulness.

15. Explain some of the knowledge representation

techniques

16. Compose the meaning of

resolution/refutation?

17.Describe the Issues in knowledge representation

17. Describe alpha beta pruning procedure

18. How would the minimax procedure have to be modified to be used by a program playing
athree or four-person game rather than two –person one?

19. Describe how will you represent facts in propositional and predicate logic with an
 example

20. Discuss Resolution in brief with an example

21. Give algorithm for propositional resolution and Unification algorithm

22. Illustrate in detail about forward and backward chaining with suitable example.

23. Discover the operation of the unification algorithm on each of the following pairs
ofliterals:
f(Marcus)and f(Caesar)
f(x) and f(g(y))
f(Marcus,g(x,y))and f(x,g(Caesar,Marcus))

24. Explain in detail about structured representation of knowledge

25. Explain about conversion to clause form algorithm in detail

26. Invent what is wrong with the following arguments

Men are widelydistributed over the earth
Socrates is a man
Therefore, Socrates is widely distributed over the earth Design.
 UNIT 3
1. What is Machine Learning?
2. Mention the difference between Data Mining and Machine learning?
3. What is ‘Overfitting’ in Machine learning?
4. Why overfitting happens?
5. How can you avoid overfitting?
6. What are the five popular algorithms of Machine Learning?
7. What are the different Algorithm techniques in Machine Learning?
8. What are the three stages to build the hypotheses or model in machinelearning?
9. What is the standard approach to supervised learning?
10. What is ‘Training set’ and ‘Test set’?
11. What is the difference between artificial learning and machine learning?
12. What are the advantages of Naive Bayes?
13. What is the main key difference between supervised and unsupervisedmachine
learning?
14. What is a Linear Regression?
15. What are the disadvantages of the linear regression model?
16. What is the difference between classification and regression?
17. What is the difference between stochastic gradient descent (SGD) and gradient
descent (GD)?
18. What are the different types of least squares?
19. What is the difference between least squares regression and multiple regression?
20. What is the principle of least squares?
21. What are some advantages to using Bayesian linear regression?
22. What Is Bayesian Linear Regression?
23. What are the advantages of Bayesian Regression?
24. What are the disadvantages of Bayesian Regression?
25. What are types of classification models?
26. Why is random forest better than SVM?
27. Which is better linear regression or random forest?
28. Which is better linear or tree based models?
29. Is linear discriminant analysis classification or regression?
30. What is probabilistic discriminative model?
31. What is SVM?
32. What is Decision tree?
33. What is Random forest?
34. What is Decision Tree Classification?
35. What Is Pruning in Decision Trees, and How Is It Done?
36. Do you think 50 small decision trees are better than a large one? Why?
37. You’ve built a random forest model with 10000 trees. You got delighted after
getting training error as 0.00. But, the validation error is 34.23. What is going on?
Haven’t you trained your model perfectly?
38. When would you use random forests vs SVM and why?

39. Assume a disease so rare that it is seen in only one person out of every million.
Assume also that we have a test that is effective in that if a person has the disease,
there is a 99 percent chance that the test result will be positive; however, the test is
not perfect, and there is a one in a thousand chance that the test result will be positive
on a healthy person. Assume that a new patient arrives and the test result is positive.
What is the probability that the patient has the disease?
40. Explain Naïve Bayes Classifier with an Example.
41. Explain SVM Algorithm in Detail.
42. Explain Decision Tree Classification.
43. Explain the principle of the gradient descent algorithm. Accompany your
explanation with a diagram. Explain the use of all the terms and constants that you
introduce and comment on the range of values that they can take.
44. Explain the following
45. Linear regression
46. Logistic Regression

UNIT 4

1. What is bagging and boosting in ensemble learning?

2. What is stacking in ensemble learning?

3. Which are the three types of ensemble learning?

4. Why ensemble methods are used?

5. What is a voting classifier?
6. What type of classifiers are used in weighted voting method?
7. What is difference between K means and Gaussian mixture?
8. What are Gaussian mixture models How is expectation maximization used in it?
9. What is the difference between K-means and KNN?
10. What is expectation maximization algorithm used for?
11. ` What is the advantage of Gaussian process?
12. What are examples of unsupervised learning?
13. How do you implement expectation maximization algorithm?
14. What is the principle of maximum likelihood?
15. Explain briefly about unsupervised learning structure?
16. Explain various learning techniques involved in unsupervised learning?
17. What is Gaussian process? And explain in detail of Gaussian parameter
estimates with suitable examples.
18. Explain the concepts of clustering approaches. How it differ from classification.
19. List the applications of clustering and identify advantages and disadvantages of
clustering algorithm.
20. Explain about EM algorithm.
21. List non-parametric techniques and Explain K-nearest neighbour estimation.

22. What is perceptron and its types?

23. Which activation function is used in multilayer perceptron?

24. What are the activation functions of MLP?

25. Does MLP have activation function?

26. What is the difference between a perceptron and a MLP?

27. What are the types of activation function?

28. What is MLP and how does it work?

29. Why do you require Multilayer Perceptron?

30. What are the advantages of Multilayer Perceptron?

31. What do you mean by activation function?

32. What are the limitations of perceptron?

33. How many layers are there in perceptron?

34. is stochastic gradient descent same as gradient descent?

35. How is stochastic gradient descent used as an optimization technique?

36. Does stochastic gradient descent lead to faster training?

37. What is stochastic gradient descent and why is it used in the training of neural
networks?

38. What are the three main types gradient descent algorithm?

39. What are the disadvantages of stochastic gradient descent?

40. How do you solve the vanishing gradient problem within a deep neural network?

41. What is the problem with ReLU?

42. Why is ReLU used in deep learning?

43. Why is ReLU better than Softmax?

44. Draw the architecture of a single layer perceptron (SLP) and explain its
operation. Mention its advantages and disadvantages.
45. Draw the architecture of a Multilayer perceptron (MLP) and explain its
operation. Mention its advantages and disadvantages.
46. Explain the stochastic optimization methods for weight determination.
47. Describe back propagation and features of back propagation.
48. Write the flowchart of error back-propagation training algorithm.
49. Develop a Back propagation algorithm for Multilayer Feed forward neural network
consisting of one input layer, one hidden layer and output layer from first principles.
50. List the factors that affect the performance of multilayer feed-forward neural
network.
51. Difference between a Shallow Net & Deep Learning Net.
52. How do you tune hyperparameters for better neural network performance?Explain
in detail.