Continuous Internal Assessment (CIA) – I
Degree: M.E. CSE | Course Code: M23CST203 | Course Name: Machine Learning
Academic Year: 2024-25 / Odd | Test: CIA-I
Total Marks: 50 | Duration: 90 minutes
Part A (Answer All Questions) – (7 × 1 = 7 Marks)
Q.No Question CO Skill Level (KX)
1 Define Machine Learning. CO1 K1
2 List two types of Machine Learning problems. CO1 K1
3 Identify any one application of Machine Learning. CO1 K2
4 What is Analytical Geometry? CO1 K1
5 What do you mean by overfitting? CO2 K1
6 Name any two evaluation metrics used for classification. CO2 K1
7 What is Cross-Validation? CO2 K2
Part B (Answer All Questions) – (5 × 2 = 10 Marks)
Q.No Question CO Skill Level (KX)
8 Illustrate the challenges in Machine Learning. CO1 K2
9 Compare generative and discriminative models. CO1 K3
10 Summarize the mathematical foundations essential for ML. CO1 K2
11 Explain the concept of model underfitting with an example. CO2 K2
12 Interpret the need for logistic regression in classification problems. CO2 K2
Part C (Answer All Questions) – (3 × 11 = 33 Marks)
Skill Level
Q.No Question Marks CO
(KX)
Examine the different types of Machine Learning problems with
13.a (11) CO1 K3
examples.
OR
13.b Analyze the advantages and disadvantages of Machine Learning. (11) CO1 K3
14.a Apply mathematical concepts such as Linear Algebra, Probability, and (11) CO1 K3
Skill Level
Q.No Question Marks CO
(KX)
Statistics to Machine Learning.
OR
14.b Assess the role of Bayesian and Decision theory in ML models. (11) CO1 K3
Develop a simple classification model using Support Vector Machines
15.a (11) CO2 K3
and discuss its evaluation.
OR
Construct a logistic regression model and explain its performance
15.b (11) CO2 K3
analysis using Cross-Validation.
KIT- Kalaignarkarunanidhi Institute of Technology
Continuous Internal Assessment (CIA) – II
Degree: M.E. CSE | Course Code: M23CST203 | Course Name: Machine Learning
Academic Year: 2024-25 / Odd | Test: CIA-II
Total Marks: 50 | Duration: 90 minutes
Part A (Answer All Questions) – (7 × 1 = 7 Marks)
Q.No Question CO Skill Level (KX)
1 What is Lasso Regression? CO2 K1
2 Define Cross-Validation. CO2 K1
3 Name any two Ensemble Methods. CO3 K1
4 What is meant by Dimensionality Reduction? CO3 K1
5 Mention one example of a clustering algorithm. CO3 K1
6 What is Principal Component Analysis (PCA)? CO3 K2
7 Define Reinforcement Learning. CO3 K1
Part B (Answer All Questions) – (5 × 2 = 10 Marks)
Q.No Question CO Skill Level (KX)
8 Distinguish between Discriminative and Generative Models. CO2 K2
9 Outline the steps in evaluating classification algorithms. CO2 K2
10 Interpret the working of K-Means clustering algorithm. CO3 K2
Q.No Question CO Skill Level (KX)
11 Describe Hierarchical Clustering. CO3 K2
12 Summarize the importance of recommendation systems. CO3 K2
Part C (Answer All Questions) – (3 × 11 = 33 Marks)
Skill Level
Q.No Question Marks CO
(KX)
Apply Support Vector Machines (SVM) for binary classification
13.a (11) CO2 K3
problems and explain with an example.
OR
Evaluate the performance of Logistic Regression models using Cross-
13.b (11) CO2 K3
Validation techniques.
Develop clustering models using K-Means and Hierarchical clustering
14.a (11) CO3 K3
for a given dataset.
OR
Analyze the role of dimensionality reduction techniques in
14.b (11) CO3 K3
unsupervised learning.
Construct a recommendation system based on collaborative filtering
15.a (11) CO3 K3
approach.
OR
Summarize the principles of Temporal Difference Learning in
15.b (11) CO3 K3
Reinforcement Learning.
KIT- Kalaignarkarunanidhi Institute of Technology
Continuous Internal Assessment (CIA) – III
Degree: M.E. CSE | Course Code: M23CST203 | Course Name: Machine Learning
Academic Year: 2024-25 / Odd | Test: CIA-III
Total Marks: 50 | Duration: 90 minutes
Part A (Answer All Questions) – (7 × 1 = 7 Marks)
Q.No Question CO Skill Level (K1)
1 Define Naïve Bayes Algorithm. CO4 K1
2 What is Maximum Likelihood Estimation? CO4 K1
Q.No Question CO Skill Level (K1)
3 What are Markov Models? CO4 K1
4 Define Perceptron in Neural Networks. CO5 K1
5 What is Backpropagation? CO5 K1
6 State any one application of Deep Learning. CO5 K1
7 List two types of Neural Networks. CO5 K1
Part B (Answer All Questions) – (5 × 2 = 10 Marks)
Skill Level
Q.No Question CO
(KX)
8 Discuss the role of Bayesian Belief Networks in Machine Learning. CO4 K2
Differentiate between Maximum Likelihood and Maximum A Posteriori
9 CO4 K2
methods.
10 Explain the working principle of Feed Forward Neural Networks. CO5 K2
11 Illustrate the components of a Convolutional Neural Network (CNN). CO5 K2
Summarize the limitations of Machine Learning addressed by Deep
12 CO5 K2
Learning.
Part C (Answer All Questions) – (3 × 11 = 33 Marks)
Skill Level
Q.No Question Marks CO
(KX)
Analyze the working of Naïve Bayes classifier and its application to
13.a (11) CO4 K3
spam email classification.
OR
Apply Markov Models for a simple weather prediction model and
13.b (11) CO4 K3
explain.
Design a basic Neural Network model to classify handwritten digits
14.a (11) CO5 K3
using Perceptron algorithm.
OR
14.b Explain in detail the Backpropagation algorithm with an example. (11) CO5 K3
Evaluate different architectures of Deep Learning models such as CNNs
15.a (11) CO5 K3
and RNNs with use cases.
Skill Level
Q.No Question Marks CO
(KX)
OR
Summarize the biological motivation behind Neural Networks and how
15.b (11) CO5 K3
it influences model design.
