Total No. of Questions : 5] SEAT No.

8
23
P6991 [Total No. of Pages : 4

ic-
[5865] - 304

tat
S.Y. M.C.A. (Mgmt. Faculty)

2s
IT - 34 : KNOWLEDGE REPRESENTATION AND

2:3
ARTIFICIAL INTELLIGENCE : ML, DL

02 71
0:0
(2020 Pattern) (Semester - III)

1
21
Time : 2½ Hours] 7/0 013 [Max. Marks : 50
Instructions to the candidates:
8/2
.23 MP

1) All Questions are compulsory.

2) For MCQ select appropriate choice from options given.
3) From Q2 to Q5 having Internal choice.
8.2 IM

82

8
4) Figures to right indicate full marks.

23
ic-
Q1) Multiple Choice Questions. [20×½=10]
16

tat
i) ________ knowledge describe relationship between various objects such

2s
as kind of, part of .
.24

2:3
1
a) Declarative b) Procedural
49

0:0
17

c) Structural d) Heuristic
21
13

ii) The wumpus world is a cave with _______ rooms.

02
P0

a) 8 b) 16
8/2

c) 4 d) 12
M
7/0

iii) _______ graph is useful for representing solution of problems that can
IM
82

8
be solved by decomposing them into a set of smaller problems.

23
.23

ic-
a) AND graph b) OR graph
16

tat
c) AND - OR graph d) Adjacency graph
8.2

2s

iv) What will backward chaining algorithm return?

.24

2:3

a) Additional statements b) Substitutes matching the query

71
49

0:0

c) Logical Statement d) Final goal

31
21

v) What is meant by compositional semantics?

1
02

a) Determining meaning b) Logical connectivities

P0
8/2

c) Semantics d) Grammer
M
7/0

vi) Inference algorithm is complete, only if it

IM
82

a) can derive any sentence

.23

b) can derive any sentence that is an entailed version

16

c) is truth preserving
8.2

d) it can derive any sentence that is an entailed version and it is truth

.24

preserving
P.T.O.
49

[5865] - 304 1
 vii) Which of the following evaluation metrics can be used to evaluate a

8
23
model while modeling a continuous output variable?

ic-
a) auc-roc b) accuracy

tat
c) logloss d) mean-squared error

2s
viii) The average squared difference between classifier predicted output and

2:3
actual output

02 71
a) mean squared error b) root mean squared error

0:0
1
c) mean absolute error d) mean relative error

21
7/0 013
ix) Naive Bayes classifiers are a collection _________ of algorithms.
a) Classification
8/2 b) Clustering
.23 MP

c) Regression d) All
x) Selecting data so as to assure that each class is properly represented in
both the training and test data.
8.2 IM

82

8
23
a) Cross-Validation b) Stratification

ic-
c) Verification d) Boot strapping
16

tat
xi) The most common Neural Networks consists of _______ network layers.

2s
a) 1 b) 2
.24

2:3
c) 3 d) 4
1
49

xii) If there is only a discrete number of possible outcomes (Called

0:0
17

Categories), the process become a

21
13

a) Regression b) Classification
02

c) Model free d) Categories

P0
8/2

xiii) ANN used for

M
7/0

a) Pattern Recognition b) Classification

IM

c) Clustering d) All
82

8
23
xiv) RNN stands for
.23

ic-
a) Recurrent Neural Network
16

tat
b) ReLU Neural Network
8.2

2s

c) Regenerate Neural Network

.24

2:3

d) Reverse Neural Network

71
49

xv) GAN stands for

0:0
31

a) Generative Advert Networks

21

b) Generative Adversarial Networks

1
02

c) General Advert Networks

P0
8/2

d) General Adversarial Networks

M
7/0

xvi) ReLU stands for

IM
82

a) Rectified Linear Unit function

.23

b) Rectified Linear Unit formula

16

c) Rectified Loss Unit function

8.2

d) Reverse Linear Unit function

.24
49

[5865] - 304 2
 xvii) Which neural network has only one hidden layer between the Input and

8
23
Output?

ic-
a) Shallow neural network

tat
b) Deep neural network

2s
2:3
c) Feed forward neural network

02 71
0:0
d) Recurrent neural network

1
21
7/0 013
xviii) Which of the following is/are limitations of deep learning?
a) Data labeling
8/2
.23 MP

b) Obtain huge training data sets

c) Data labeling and obtain huge training data sets
8.2 IM

82

8
23
d) None of these

ic-
xix) The FPGAs can be used to implement _______
16

tat
2s
a) a Software design
.24

2:3
b) Hardware design
1
49

0:0
17
c) both Hardware & Software designs
21
13

d) none
02
P0

xx) Which of the following most advanced form of AI?

8/2

a) Neural Network b) Machine learning

M
7/0

c) Data Science d) Deep learning

IM
82

8
23
.23

Q2) a) What is Artificial Intelligence? Discuss the main branches of Artificialic-

16

tat
Intelligences. [4]
8.2

2s
.24

b) Show that “If I look into the sky and I am alert then, I will see a dim star
2:3
71

or if I am not alert then I will not see a dim star” is valid. [6]
49

0:0
31

OR
21
1

a) Write a FOL of following statements: [6]

02
P0
8/2

i) None of my friends are perfect.

M

ii) Every student smiles.

7/0

iii) Every student walks or talks.

IM
82

iv) Every student who loves Yash is Happy.

.23

v) Anyone who loves everyone loves himself.

16

vi) Someone Dance and someone singing.

8.2

b) Explain properties of good knowledge based system. [4]

.24
49

[5865] - 304 3
Q3) a) Differentiate between supervised and unsupervised learning. [4]

8
23
b) The values of independent variable x and dependent variable y are given

ic-
below.

t
sta
x 0 1 2 3 4
y 2 3 5 4 6

2
2:3
Find the least square regression line y = ax + b. Estimate the value of y

02 71
0:0
when x is 10. [6]

1
21
OR
a) 7/0 013
To evaluate the performance of a trained model confusion matrix plotted
which is given below. [6]
8/2
.23 MP

0 1
IMlabel

0 61 3
82

8
8.2 True

23
1 3 104

ic-
16

Predicated label

tat
2s
b) Define machine learning? Briefly explain the types of machine learning.[4]
.24

2:3
1
49

0:0
17
Q4) a) Why we do use pooling layers in CNN? [4]
b) How ReLU activation function works in CNN? [6]
21
13

OR
02
P0

a) Explain uses and application of Deep learning. [4]

8/2

b) Why we need Back propagation? Explain Back propagation Algorithm.[6]

M
7/0
IM
82

8
23
Q5) Write a short notes on [10]
.23

ic-
a) Application of AI.
16

tat
b) LSTM
8.2

2s

c) Training Data and Testing Data.

.24

2:3

d) Key processor of AI.

71
49

0:0

e) NLP
31

OR
21
1

a) Limitations of AI.
02
P0

b) Linear Regression.
8/2

c) Essentials of Data Analysis.

M
7/0

d) Data center.
IM
82

e) Chat bot.
.23


16
8.2
.24
49

[5865] - 304 4