Scribd
Upload
93 views4 pages

CS-601-CBGS: B.Tech., VI Semester

This document contains 8 questions related to machine learning. It discusses various machine learning concepts like preprocessing of data, supervised and unsupervised models, neural networks, reinforcement learning, and support vector machines. It asks students to explain processes, compare algorithms and models, discuss applications, and write short notes on specific topics in machine learning.

Uploaded by

Dawar Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
93 views4 pages

CS-601-CBGS: B.Tech., VI Semester

This document contains 8 questions related to machine learning. It discusses various machine learning concepts like preprocessing of data, supervised and unsupervised models, neural networks, reinforcement learning, and support vector machines. It asks students to explain processes, compare algorithms and models, discuss applications, and write short notes on specific topics in machine learning.

Uploaded by

Dawar Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Total No. of Questions : 8] [1] [Total No.

of Printed Pages : 4

Roll No ..................................
CS-601-CBGS
B.Tech., VI Semester
Examination, December 2020
Choice Based Grading System (CBGS)
Machine Learning
Time : Three Hours
Maximum Marks : 70
Note: i) Attempt any five questions.
{H$Ýht nm±M àíZm| H$mo hb H$s{OE&
ii) All questions carry equal marks.
g^r àíZm| Ho$ g_mZ A§H$ h¢&
iii) In case of any doubt or dispute the English version
question should be treated as final.
{H$gr ^r àH$ma Ho$ g§Xoh AWdm {ddmX H$s pñW{V ‘| A§J«oOr ^mfm
Ho$ àíZ H$mo A§{V‘ ‘mZm Om¶oJm&

1. a) Explain the machine learning concept by taking an


example. Describe the perspective and issues in machine
learning.
Machine learning Ho$ {gÕmÝV H$mo EH$ CXmhaU boVo hþE g‘PmB¶o.
Machine learning Ho$ Ñ{ï>H$moU VWm MwZm¡Vr H$mo ~VmBE&
b) What is the role of preprocessing of data in machine
learning? Why it is needed? Explain the unsupervised
model of machine learning in detail with an example.
Machine learning ‘| data preprocessing H$s ³¶m ^y{‘H$m h¡?
BgH$s ³¶m| Amdí¶H$Vm h¡? Machine learning Ho$ unsupervised
model H$s {dñV¥V ê$n go CXmhaU g{hV ì¶m»¶m H$s{O¶o&

CS-601-CBGS PTO

https://www.rgpvonline.com
[2]

2. a) Discuss linear regression with an example. Explain the


role of hypothesis function in machine learning models.
Linear regression H$mo CXmhaU Ho$ gmW g‘PmBE. machine
learning models ‘| hypothesis function H$s ^y{‘H$m H$s ì¶m»¶m
H$a|&
b) Explain the concept of perceptron, back propagation and
sigmoid activation function in brief. Differentiate
between classification and regression.
perceptron, back propagation Ed§ sigmoid activation
function{gÕm§V H$s g§jno ‘| ì¶m»¶m H$s{O¶o. classification Ed§
regression Ho$ ‘ܶ A§Va H$mo ~VmB¶o.

3. a) What are the different types of Neural networks? Explain


the convolution neural network model in detail.
Neural networks Ho $ {d{^Þ àH$ma H$m¡ Z -H$m¡ Z -go h¡ ?
convolution neural network model H$s {dñV¥V ê$n go ì¶m»¶m
H$s{O¶o.
b) Explain the multilayer perceptron model in detail with
neat diagram.
Multilayer perceptron model H$s ñdÀN> aoIm{MÌ H$s ‘XX go
{dñV¥V ì¶m»¶m H$a|&

4. a) Explain the concept of different layers in Neural network.


What do you mean by the term convolution layer, pooling
layer, loss layer, dense layer? Describe each one in brief.
Neural network ‘| {d{^Þ layers H$s ì¶m»¶m H$s{O¶o& convolution
layer, pooling layer, loss layer, Ed§ dense layer go Amn ³¶m
g‘PVo h¢? à˶oH$ H$s g§{já ì¶m»¶m H$a|&
CS-601-CBGS PTO
Contd...

https://www.rgpvonline.com
[3]

b) Explain the process of Sub-sampling of input data in neural


network model. Some of the features of Keras framework
for implementing neural networks models.
Neural network model ‘|o input data Ho$ Sub-sampling àH«$‘
H$mo g‘PmBE. neural network model H$mo {H«$¶mpÝdV H$aZo Ho$
{bE Keras framework Ho$ Hw$N> CëboIZr¶ JwUm| H$mo ~VmBE&
5. a) What do you mean by Recurrent neural network? Explain
with the help of a diagram. In which cases this model is
suitable.
Recurrent neural network go Amn ³¶m g‘PVo h¡? aoIm{MÌ
H$s ‘XX go ì¶m»¶m H$a|& {H$g pñWVr ¶h model Cn¶wº$ h¡&
b) Explain the Actor critic model. List down what are its
advantages in reinforcement learning.
Actor critic model H$s ì¶m»¶m H$a|& Reinforcement learning
‘§o BgHo$ ’$m¶Xm| H$mo gyMr~Õ H$s{O¶o.
6. a) Explain the concept of Reinforcement Learning and its
framework in details.
Reinforcement Learning VWm CgHo$ T>m§Mo H$s {dñV¥V ê$n go
ì¶m»¶m H$s{O¶o&
b) Describe how principle component analysis is carried out
to reduce the dimensionality of data sets.
~VmBE H$s {H$g àH$ma data sets Ho$ Am¶m‘m| H$mo H$‘ H$aZo Ho$ {bE
principle component analysis H$mo A§Om‘ {X¶m OmVm h¡?

7. a) Describe Q-learning in brief. What is SARSA algorithm?


Explain this.
Q-learning H$mo g§jon ‘| ~VmBE SARSA algorithm ³¶m h¡?
ì¶m»¶m H$s{O¶o&

CS-601-CBGS PTO

https://www.rgpvonline.com
[4]

b) Explain the difference between Value iteration and Policy


iteration. What is Markov Decision Process (MDP)?
iteration Ed§ Policy iteration Ho$ ‘ܶ A§Vam| H$s ì¶m»¶m H$s{O¶o
Markov Decision Process àH$‘ (MDP) ³¶m h¢?

8. a) Write short notes on any two:


i) Natural language processing
ii) Application of machine learning in computer vision
iii) Bayesian networks
{H$Ýht Xmo na g§{já {Q>ßnUr {bIo&
i) Natural language processing
ii) computer vision Ho$ joÌ ‘| machine learning H$m AZwà¶moJ
iii) Bayesian networks
b) Explain the concept and role of support vector machine
in details. Also, describe its application areas.
support vector machine Ho$ {gÕm§V VWm ^y{‘H$m H$s ì¶m»¶m
H$s{O¶o& BgHo$ A{V[aº$ BgHo$ {d{^Þ AZwà¶moJ joÌ H$mo ^r ~VmBE&

******

CS-601-CBGS PTO

https://www.rgpvonline.com

You might also like