CS/B.
TECH(N)/0DD/SEM-5/5937/2024-2025/\036
MAULANAABUL KALAM AZAD UNIVERSITY OF TECHNOLOGY, WEST RENe.
Paper Code: ESC(CSBS) 502/PCC-Al 502/PCCAIML 502 Machine Learning
Ucch
UPID: 005937
Time Allotted:3Hours
Full Marks :70
The Figures in the margin indlcate full marks,
Candidote are required to give their answers in their own words us fur as practicable
Group-A (Very Short Answer Type Question)
1. Answer any ten of the tollowing : (1x 10= 10 )
( What are outliers?
(1)
(1)
Which of the folowing ensemble model helps in reducing variance? Embied
isthe machine learning algorithms that can be used with labeled data
is a part of machine learning that works with neural networks
(V) Where does the Hidden MarkoV Model is used?
(I) How many types of Artificial. Neural NetworkS?
(Va) What is Auto Association Task?
(vi) What are independent vatiables?
(X) Suppose you have picked the parameter for a model using [Link] validation (C). Which of the foliowing is
the best way to pick a final model tó use anhd estimate its error?
() The model will be trainedwith datain one single batch is known as ?
(x) Which suggests the existence of an efficient recursive algorithm for online smoothing?
.
(X1) stands for, Statistical Information Grid.
Group-B (`hort Answer. Type Question)
Answer any three of thefollowing : [5x3 = 15]
2. What are the different týpes of clu[tering álgorithms available? Which onewould you recommend for a
given problem?
3. What is Overfitting ? [Link] you avoidit?
4 What is the role of the Activation fünctions in NeuralNetworks?
5. Why SVM is an example of a large margin classifier?
6. Compare SVM and Logistic Regression in, handling outliers.
Group-C (Long Answer Type Question)
Answer any three of the following : [15 x3=45 ]
(51
7. (a) Explain Perceptron.
(b) what do you mean by Neural Network. [5)
(c) How doyou choose the Scaling method ú[ed for NeuralNetworks? [41
(a) What is linear regression?
[6]
(b) State the assumptions in a linear regression model: (5]
(c) What is feature engineering? How do yoç, apply it in the process of modelling? l
9. (a) Explain Random Forest 'method with suitable example,
(b) Explaín K-Means Clustering algorithm with suitable example. 6]
10. (a) How do you select important variables while working ona data set? (6]
(D) here are many machine learning algorithms till now.
If eiven a data set, how can one determine
( which algorithm to be used for that?
[3.
unsupervised machine learning?
() what is the main key difference between supervised and (5)
11. (a) What do you mean Model Averaging? (10)
(b) How to Average Models? Explain with suitable example.
*** END OF PAPER ***
1/1