20CB/CS/DS/IT602
Hall Ticket Number:
III/IV B.Tech (Regular) DEGREE EXAMINATION
July/August, 2023 Common to CB,CSE,DS &IT Branches
Sixth Semester Machine Learning
Time: Three Hours Maximum: 70 Marks
Answer question 1 compulsory. (14X1 = 14Marks)
Answer one question from each unit. (4X14=56 Marks)
CO BL M
1 a) What is machine learning and how does it differ from traditional programming? CO1 L1 1M
b) List out any five different context where machine learning is applicable. CO1 L1 1M
c) What is mini-batch gradient descent and how does it differ from batch gradient descent? CO1 L2 1M
d) Define Overfitting and Underfitting. CO2 L1 1M
e) Define entropy and write down its formula. CO2 L2 1M
f) What is logistic regression, and how does it handle binary classification problems? CO2 L1 1M
g) How is accuracy measured using cross-validation? CO3 L2 1M
h) Discuss the precision/recall trade-off and how it impacts classifier performance CO3 L1 1M
i) How does the hierarchical clustering algorithm work, and what are its advantages? CO4 L2 1M
j) Define support vector. CO4 L2 1M
k) Write about Lasso Regression CO1 L1 1M
l) Differentiate Supervised Learning and Unsupervised Learning CO4 L1 1M
m) What is Confusion Matrix? How to create it? CO3 L1 1M
n) Explain about Bagging and Voting. CO3 L1 1M
Unit-I
2 a) What are the main types of machine learning systems? Describe each type and provide CO1 L1 7M
examples of their applications?
b) What are the typical steps involved in developing a machine learning application? Provide CO1 L2 7M
an overview of the process. What are some evaluation metrics used to assess the
performance of machine learning models,
(OR)
3 a) How do you choose the right machine learning algorithm for a given problem or task? CO1 L2 7M
Explain the process of understanding the problem domain, data characteristics, and
selecting the appropriate algorithm based on factors like the nature of the problem,
available data, and desired outcomes?
b) What are the key Python libraries used in machine learning? Provide an overview of few CO1 L1 7M
libraries and their roles in tasks such as data manipulation, visualization, and model
training?
Unit-II
4 a) Explain in detail about CART algorithm with an example. CO2 L2 7M
b) Explain in detail about SVM with an example. CO2 L2 7M
(OR)
5 a) How to measure the accuracy of a classifier? Explain the concept of cross-validation and CO2 L1 7M
how it helps in estimating the model's performance on unseen data?
b) How can you train and use a Naïve Bayes classifier for classification tasks? Explain the CO2 L3 7M
steps involved in estimating the class priors and conditional probabilities and making
predictions based on the maximum posterior probability?
P.T.O
20CB/CS/DS/IT602
Unit-III
6 a) What is the precision/recall trade-off, and how does it relate to the classifier's decision CO3 L3 7M
threshold? Discuss how adjusting the threshold affects the precision and recall values and
how to choose an appropriate threshold based on the specific application requirements?
b) How do ensemble methods address the bias-variance trade-off? Discuss how combining CO3 L2 7M
multiple classifiers reduces variance and can help to create more robust and accurate
models?
(OR)
7 Explain in detail about Ada boost and Gradient boost with examples. CO3 L1 14M
Unit-IV
8 a) How does the growth function in computational learning theory relate to the sample CO4 L3 7M
complexity? Explain the growth function as a measure of the number of distinct
dichotomies that can be generated by a hypothesis space and its impact on the learnability
of a concept?
b) What is the Gaussian mixture model (GMM) in unsupervised learning? Explain the concept CO4 L3 7M
of representing the underlying data distribution as a mixture of Gaussian components and
using the Expectation-Maximization (EM) algorithm to estimate the parameters?
(OR)
9 a) How does hierarchical clustering work? Explain the top-down and bottom-up approaches CO4 L1 7M
of building a hierarchical cluster tree by iteratively merging or splitting clusters based on
similarity measures?
b) Explain in detail about K-means Clustering Algorithm with an example. CO4 L2 7M
