JSS MAHAVIDYAPEETHA

JSS SCIENCE AND TECHNOLOGY UNIVERSITY

SRI JAYACHAMARAJENDRA COLLEGE OF ENGINEERING
 Constituent College of JSS Science and Technology University
 Approved by A.I.C.T.E
 Governed by the Grant-in-Aid Rules of Government of Karnataka
 Identified as lead institution for World Bank Assistance under TEQIP Scheme

Course Title: Machine Learning Course Code: 20CS610

Credits: 4 Contact Hours (L: T: P): 52:0:0
Type of Course: Theory Category: Professional Core Course
CIE Marks: 50 SEE Marks: 100

Pre-requisite:Linear algebra, Elementary probability and statistics, Knowledge of programming in

some language.
Course Objectives: The course should enable the students to:
Sl.
Course Objectives
No.
1 Understand the basic concepts of Machine Learning.
2 Formulate machine learning problems corresponding to different applications.
3 Understand the unsupervised learning techniques.
4 Understanding the pre-processing activity done for Machine learning algorithm.
5 Understand neural networks implemented for various applications.

Unit No. of
Course Content
No. Hours
1 Introduction: What Is Machine Learning? Applications of Machine Learning, 10
Types of Machine Learning, Statistical Decision Theory and Analysis.
Probability: Introduction, Basics of Probability, Combination, Permutation,
union, Intersection. Complement, Conditional Probability, Random Variables,
Binomial Distribution, Normal distribution, Joint Distributions and Densities,
Moments of Random Variables.
2 Statistical Decision Making: Introduction, Bayes Theorem, Multiple Features, 12
Conditionally Independent Features, Decision Boundaries.
Decision Tree: Information gain, Entropy, Gini-index, building Decision Tree
with example problems.
Nonparametric Decision Making: Introduction, Histograms, kernel and
Window Estimators, K-Nearest Neighbour Classification Techniques, Adaptive
Decision Boundaries, Adaptive
3 Clustering: Introduction, Hierarchical Clustering: Agglomerative Clustering 10
Algorithm, The single Linkage Algorithm, The Complete Linkage Algorithm,
The Average–Linkage Algorithm, Partitional Clustering: Forgy’s Algorithm, The
K-Means Algorithm.
4 Dimensionality Reduction: Introduction, Singular Value Decomposition, 8
Principal Component Analysis, Linear Discriminant Analysis.
5 Multilayer Perceptron: Introduction to ANN, Perceptron, types of activation 12
function training a Perceptron, Learning Boolean Functions, Multilayer Perceptron
(MLP), Back Propagation Algorithm
JSS MAHAVIDYAPEETHA
JSS SCIENCE AND TECHNOLOGY UNIVERSITY
SRI JAYACHAMARAJENDRA COLLEGE OF ENGINEERING
 Constituent College of JSS Science and Technology University
 Approved by A.I.C.T.E
 Governed by the Grant-in-Aid Rules of Government of Karnataka
 Identified as lead institution for World Bank Assistance under TEQIP Scheme

Text Books:
Sl.N
Author/s Title Publisher Details
o.
1 Earl Gose, Richard Pattern Recognition and Pearson 2015
Johnsonbaugh Steve Jos Image Analysis
2 Richard O. Duda, Peter E. Pattern Classification Second edition, Wiley
Hart, David G. Stork publication
3 EthemAlpaydin Introductionto Thirdedition, MIT
MachineLearning Press,https://www.cmpe.boun
.edu.tr/~ethem/i2ml3e/

Reference Books:
Sl.N
Author/s Title Publisher Details
o.
1 Tom M. Mitchell Machine Learning McGraw-Hill Publishers,1997
2 Christopher M. Bishop Pattern Recognition and Springer Publishers,2011.
Machine Learning
3 ShaiShalev-Shwartz and Understanding Machine Cambridge University press.
ShaiBendavid Learning 2017.
4 Kevin Murphy Machine Learning: A MIT Press,2012
Probabilistic Perspective

Web Resources:
Sl.
Web Link
No.
1 https://nptel.ac.in/courses/106/105/106105032/
2 https://nptel.ac.in/courses/117/105/117105079/

Course Outcomes:
CO1 Use the concepts of probability and combinatorics, statistics to solve the real world
problems.
CO2 Design simple ML algorithms using Bayes theorem, decision tree, and KNN for
classification of real life patterns.
CO3 Apply different types of clustering techniques to categorize data in any given dataset.
CO4 Apply various dimensionality reduction techniques to select robust feature sets.
CO5 Design MLP to perform digit, character and image classification

Mapping Course Outcomes with Program Outcomes & Program Specific Outcomes:
Course Program Outcomes PSO’s
Outcomes PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 P012 PSO1 PSO2 PSO3 PSO4
CO1 3 3 3 3 - - - - - - - - 3 - 3 -
CO2 3 3 3 3 - - - - - - - - 3 - 3 -
CO3 3 3 3 3 - - - - - - - - 3 - 3 -
CO4 3 3 3 3 - - - - - - - - 3 - 3 -
CO5 3 3 3 3 - - - - - - - - 3 - 3 -
1-Low association, 2-Moderate association, 3-High association