Iat2 ML

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

V V COLLEGE OF ENGINEERING

V V Nagar, Arasoor, Tisaiyanvilai


INTERNAL ASSESSMENT TEST – II
I ME CSE / II Semester (EVEN) (Batch 2023-2025)
Department of Computer Science and Engineering

Sub. Code / Name : CP4252/ Machine Learning`


Date / Session : 04.06.2024 / AN Max. Marks: 50 Marks
Sem / Branch : I / CSE Duration: 1.30 Hrs
PART A (5 x 2 = 10 Marks) MA L CO MS

1 Why use Unsupervised Learning? 2 L5 CO3

2 Differentiate between prior and posterior probabilities. 2 L4 CO4


Give an example of a real-world application of Bayesian Belief
3 2 L4 CO4
Networks.
4 Why are neural networks important? 2 L5 CO5
5 How does Perceptron work? 2 L5 CO5
PART B (2 x 13 = 26 Marks) MA L CO MS

6 a. Classify the types of Naïve Bayes Model and list out its advantages 13 L5 CO4
and disadvantages.

Explain Hidden Markov Models (HMMs) and their applications.


b. Describe the algorithms used for solving problems in HMMs, such 13 L3 CO4
as the Forward-Backward algorithm and the Viterbi algorithm.

Describe the architecture of a Feed Forward Neural Network


13 L6 CO5
7 a. (FFNN). How does information flow through the network from
input to output?
(OR)
Explain the backpropagation algorithm in detail. How does it update
b 13 L4 CO5
the weights in a neural network?
PART C (2 × 7 = 14 Marks) MA L CO MS
What are Bayesian Belief Networks (BBNs)? Discuss their
8 a. components and how they can be used to model complex 7 L2 CO4
probabilistic relationships.
(OR)
Describe the Maximum Likelihood Estimation (MLE) method and
b how it differs from Maximum A Posteriori (MAP) estimation. 7 L6 CO4
Include mathematical formulations and examples for both.
Describe the Expectation-Maximization (EM) algorithm. What are
9 a. 7 L2 CO3
the main steps involved, and how does it work?
(OR)
Explain the concept of Principal Component Analysis (PCA). What
b 7 L4 CO3
is its main purpose, and how does it work?

L1- Remember L2 - Understand L3 - Apply L4 - Analyze L5 - Evaluate L6 – Create


MA: Marks L: Level CO: Course Outcome MS: Marks Scored

CO3: Implement Probabilistic Discriminative and Generative algorithms for an application and analyze the results.
CO4: Use a tool to implement typical Clustering algorithms for different types of applications.
CO5: Design and implement an HMM for a Sequence Model type of application and identify applications suitable for
different types of Machine Learning with suitable justification.

PART A PART B PART C Total Total


Marks Marks
Marks Marks Marks Marks Marks Marks Allotted Scored
Allotted Scored Allotted Scored Allotted Scored

CO5 4 13 17

CO4 4 13 7 24

CO3 2 7 9

Skills Part A Part B & C Total Percentage

HOTS 1,2,3,4,5 6a, 7a, 7b, 8b, 9b 70%


(L4, L5, L6)
LOTS - 6b, 8a, 9a 30%
(L1, L2, L3)

HOTS: Higher Order Thinking Skills; LOTS : Lower Order Thinking Skills

Staff Incharge HOD

IQAC Incharge Principal

You might also like