NAC/TLP-

Format No.
07a
Nadar Saraswathi College of Engineering and Technology,
Rev. No.
Vadapudupatti, Theni - 625 531
Date
(Approved by AICTE, New Delhi and Affiliated to Anna University, Chennai)
Total Pages 08

Question Bank for the Units – I to V

SEM- VI Semester – B.E.

06

BR- Department of Electrial and Electronics Engineering

104

CS CS3491- ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Part-A (10 x 2 = 20 Marks)

UNIT – I

No Question Level Competence Ma

rk

1.1 What is Artificial Intelligence? BTL1 Remembering 2

1.2 What is an agent? BTL1 Remembering 2

1.3 What are the different types of agents? BTL1 Remembering 2

1.4 What are various applications of AI? or What can AI do BTL2 Understanding 2
today?

1.5 What is the application of BFS? BTL2 Understanding 2

2.1 List some of the uninformed search techniques BTL2 Understanding 2

2.2 What is the power of heuristic search? (or) Why does one BTL1 Remembering
2
go for heuristics search?

2.3 How can we avoid ridge and plateau in hill climbing? BTL1 Remembering 2

2.4 What is CSP? BTL1 Remembering 2

2.5 State the reason when hill climbing often gets stuck? BTL2 Understanding 2

UNIT-II

3.1 Why does uncertainty arise? BTL1 Remembering 2

3.2 What is the need for probability theory in uncertainty? BTL2 Understanding 2

3.3 Differentiate uncertainty with ignorance BTL2 Understanding 2

3.4 What is the need for utility theory in uncertainty? BTL2 Understanding 2
3.5 Define principle of maximum expected utility (MEU)? BTL1 Remembering 2

4.1 Mention the needs of probabilistic reasoning in AI BTL1 Remembering 2

4.2 What does the full joint probability distribution specify? BTL2 Understanding 2

4.3 State Bayes' Theorem in Artificial Intelligence. BTL1 Remembering 2

4.4 Given that P(A)=0.3,P(A|B)=0.4 and P(B)=0.5, Compute BTL1 Remembering

2
P(B|A).

4.5 What is Bayesian Belief Network? BTL1 Remembering 2

4.6 Define uncertainty BTL1 Remembering 2

4.7 State Bayes rule BTL2 Understanding 2

UNIT III

5.1 What is Machine Learning? BTL1 Remembering 2

5.2 Why overfitting happens? BTL2 Understanding 2

5.3 What are the different Algorithm techniques in Machine BTL2 Understanding
2
Learning?

5.4 What is Training data set and test set? BTL2 Understanding 2

5.5 What is the main key difference between supervised and BTL1 Remembering
2
unsupervised machine learning?

6.1 What is a Linear Regression? BTL1 Remembering 2

6.2 What is the difference between least squares regression BTL2 Understanding
2
and multiple regression?

6.3 What Is Bayesian Linear Regression? BTL1 Remembering 2

6.4 Why is random forest better than SVM? BTL1 Remembering 2

6.5 You’ve built a random forest model with 10000 trees. BTL1 Remembering
You got delighted after getting training error as 0.00.
2
But, the validation error is 34.23. What is going on?
Haven’t you trained your model perfectly?

UNIT IV

7.1 What is bagging and boosting in ensemble learning? BTL1 Remembering 2

7.2 Which are the three types of ensemble learning? BTL2 Understanding 2

7.3 What is difference between K means and Gaussian BTL2 Understanding

2
mixture?

7.4 What are Gaussian mixture models How is expectation BTL2 Understanding
2
maximization used in it?

8.1 What is the difference between K-means and KNN? BTL1 Remembering 2
8.2 How do you implement expectation maximization BTL1 Remembering
2
algorithm?

8.3 What is the principal maximum likelihood? BTL2 Understanding 2

8.4 What type of classifiers are used in weighted voting BTL1 Remembering
2
method?

UNIT V

9.1 What is perceptron and its types? BTL1 Remembering 2

9.2 Which activation function is used in multilayer perceptron? BTL2 Understanding 2

9.3 What are the activation functions of MLP? BTL2 Understanding 2

9.4 What is the difference between a perceptron and a MLP? BTL2 Understanding 2

10.1 Why is ReLU better than Softmax? BTL1 Remembering 2

10.2 What is the problem with ReLU? BTL1 Remembering 2

10.3 What are the disadvantages of stochastic gradient descent? BTL2 Understanding 2

10.4 What is stochastic gradient descent and why is it used in BTL1 Remembering
2
the training of neural networks?

Part – B ( 5 x 13 = 65 Marks)and Part C(15 Marks)

UNIT- I

11.a-1 Explain characteristics of Intelligent agents. BTL1 Remembering (13)

11.a-2 Discuss all the Uninformed search methods with examples. BTL2 Understanding (13)

11.a-3 Differentiate Blind search & Heuristic search. BTL1 Remembering (13)

11.a-4 Discuss different types of informed search strategies BTL2 Understanding (13)

11.b-1 Explain the A* search and give the proof of optimality of A* BTL2 Understanding (13)

11.b-2 Explain AO* algorithm with a suitable example. State the BTL4 Analyzing (13)
limitations in the algorithm?

11.b-3 State the constraints satisfaction problem. Outline local search BTL2 Evaluating (13)
for constraint satisfaction problem with an example.

11.b-4 Explain alpha-beta pruning algorithm and the Min max game BTL6 Creating (13)
playing algorithm with example?

UNIT- II

Define uncertain knowledge, prior probability and

12.a-1 (13)
conditional probability. BTL1 Remembering
12.a-2 State the Bayes’ theorem. How it is useful for decision (13)
making underuncertainty? Explain belief networks briefly? BTL1 Remembering

Explain the method of handling approximate inference in (13)

12.a-3 Bayesian networks. BTL2 Understanding

12 a-4 Construct a Bayesian Network and define the necessary (13)

CPTs for the given scenario. BTL2 Understanding

What is Bayes’ rule? Explain how Bayes’ rule can be (13)

12.b-1 BTL1 Remembering
applied to tackle uncertain Knowledge.

12.b-2 Discuss about Bayesian Theory and Bayesian network. (13)

BTL2 Understanding

12.b-3 How to get the exact inference form Bayesian network? (13)
BTL1 Remembering

12.b-4 Elaborate an conditional and unconditional probability with (13)

an example BTL1 Remembering

UNIT- III

13.a-1 ExplainNaïveBayesClassifierwith anExample.

(13)
BTL1 Remembering

13 a-2 ExplainSVMAlgorithminDetail. (13)

BTL1 Remembering

13.a-3 ExplainDecisionTreeClassification. (13)

BTL2 Understanding

13.a-4 Explain the principle of the gradient descent algorithm. BTL2 Understanding
(13)
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.

Explain in detail about linear regression (13)

13.b-1
BTL1 Remembering

13.b-2 Explain in detail about Logistic regression (13)

BTL2 Understanding

13.b-3 Describe in detail about random forest (13)

BTL1 Remembering

13.b-4 What is a classification tree.Explain the steps to construct (13)

BTL2 Evaluating
classification tree.List and explain about the different
procedures used.

13.b-5 State when and why you would use random forests vs (13)
BTL2 Evaluating
SVM?

UNIT IV

14.a-1 Explainbrieflyaboutunsupervisedlearningstructure?
 (13)
BTL1 Remembering

14 a-2 List the classification of clustering & identify advantages & (13)
BTL1 Remembering
disadvantages of clustering algorithms.

14 a-3 (13)
Listnon-parametrictechniquesandExplainK- BTL2 Understanding
nearestneighbourestimation.

14 b-1 Describe in detail about K means clustering (13)

BTL2 Understanding

14 b-2 Explain about Expectation maximization algorithm. (13)

BTL1 Remembering

14 b-3 Describe about ensemble learning techniques. (13)

BTL2 Understanding

14 b-4 Explain about gaussian mixture models (13)

BTL1 Remembering

14 b-5 Outline the steps in adaboost algorithm with an example. (13)

BTL2 Understanding

Unit – V

15.a-1 Drawthearchitectureofasinglelayerperceptron(SLP)andexp
lainits operation. Mention its advantages and (13)
BTL1 Remembering
disadvantages.

15 a-2 DrawthearchitectureofaMultilayerperceptron(MLP)andex BTL1 Remembering

(13)
plainits operation. Mention its advantages and
disadvantages.

15 a-3 Develop a Back propagation algorithm for Multilayer Feed (13)

BTL2 Understanding
forward neural network consisting of one input layer, one
hidden layer and output layer from first principles

15 b-1 DifferencebetweenaShallowNet &DeepLearningNet. BTL2 Understanding

(13)

15 b-2 How do you tune hyperparameters for better neural BTL1 Remembering
(13)
network performance? Explain in detail.

15 b-3 Explainthestochasticoptimizationmethodsforweightdetermi BTL2 Understanding

(13)
nation.

15 b-4 Describe in detail about batch normalization ,Relu and (13)

BTL1 Remembering
regularization
 L1: Knowledge, L2: Comprehension, L3: Application, L4: Analysis, L5: Evaluation, L6: Synthesis

Bloom’s
COs Outcomes
Taxonomy

C305.1 Use appropriate search algorithms for problem solving L1

C305.2 Apply reasoning under uncertainty L2

C305.3 Build supervised learning models L4

C305.4 Build ensembling and unsupervised models L3

C305.5 Build deep learning neural network models L4