INDUS INSTITUTE OF TECHNOLOGY& ENGINEERING

Constituent Institute of Indus University

Subject: Machine Learning

Program: B Tech CSE Subject Code: CS0701 Semester: VII
Teaching Scheme (Hours per week) Examination Evaluation Scheme (Marks)
Continuous Continuous
University University Internal Internal
Lecture Tutorial Practical Credits Theory Practical Evaluation Evaluation Total
Examination Examination (CIE)- (CIE)-
Theory Practical
3 0 2 4 40 40 60 60 200

Course Objectives:
1. Understand the key algorithms and theory that form the foundation of Machine Learning.
2. Understand a wide variety of learning algorithms.
3. Recognize the characteristics of machine learning that make it useful to real-world problems.
4. Understand how to perform evaluation of learning algorithms and model selection.
5. Develop skills of using recent machine learning software in order to solve practical problems.
6. Understand and learn state of the art machine learning techniques to provide employability in
industry.

CONTENTS

UNIT-I
[12 hours]

Introduction
Learning Problems, designing a learning system, Issues with machinelearning.Concept Learning,
Version Spaces and Candidate Eliminations, Inductivebias, Supervised/Unsupervised Learning,
Loss functions andgeneralization, Parametric vs Non-parametric methods,Evaluating Machine
Learning algorithms and Model Selection,
Introduction to Statistical Learning Theory, Ensemble Methods, Bagging, Boosting, Random
Forest
 UNIT-II
[12 hours]
Supervised Learning (Regression/Classification)
Basic methods: Distance-based methods, Nearest-Neighbors,Decision Trees, Naive Bayes,
Linear models: Linear Regression, Logistic Regression, GeneralizedLinear Models, Support
Vector Machines, Nonlinearity and Kernel Methods, Beyond Binary Classification: Multi-
class/Structured Outputs,Ranking
Unsupervised Learning
Clustering: K-means/Kernel K-means, Dimensionality Reduction -PCA, CCA, LDA, ICA, MNF
– CanonicalVariates - Feature Selection vs Feature Extraction, Generative Models (mixture
models and latent factor models)

UNIT-III
[12 hours]

Bayesian Learning
Bayes Theorem, Bayes Theorem and Concept Learning, MaximumLikelihood and Least squared
Error Hypothesis, Maximum likelihood hypothesis for Predicting Probabilities, Minimum
Description Length, Principle, Bayes Optimal Classifier, Gibbs Algorithm, Naïve Bayes,
Classifier, Bayesian Belief Network, EM Algorithm, Case Study: Learning to classify text

UNIT-IV
[12 hours]

Artificial Neural networks

Neural Network Representation, Appropriate problems for Neural NetworkLearning, Perceptron,
Multilayer Networks and Back Propagation, Algorithms, Remarks on Back Propagation
Algorithms, Case Study: face Recognition
Advanced topics
Semi-supervised, Active Learning, Reinforcement Learning, Recent trends in various learning
techniques of machine learning and classification methods, Overview of typical application
areas, such as Recommender System

Course Outcomes:

At the end of this subject, students should be able to:

1. Get exposure of machine learning concepts and range of problems that can be handled
by machine learning
2. Compare and parameterize different learning algorithms
3. Apply the machine learning concepts in real life problems
4. Understand learning in machines with different techniques
5. Understand and apply various recognition techniques.
 6. Learn about parameter selection and feature extraction.

Text Books:

1. Tom M Mitchell, “Machine Learning”, McGraw Hill.

2. Peter Harrington, “Machine Learning in Action”, DreamTech.

Reference Books:

1. Henrik Brink, Joseph Richards, Mark Fetherolf, “Real-World Machine Learning”,

DreamTech
2. Christopher Bishop, “Pattern Recognition and Machine Learning, ”Hastie, Tibshirani, and
Friedman, “Elements of Statistical Learning”. Springer
3. Jiawei Han and Michelline Kamber, “Data Mining: Tools and Techniques”, 3rdEdition.
4. I H Witten, Eibe Frank, Mark A Hall, “Data Mining: A practical Machine LearningTools and
techniques”, Elsevier

Web Resources:

1. Couresera.org: Machine Learning by Andrew Ng, Stanford University

LIST OF EXPERIMENTS

Experi Title Learning Outcomes

ment.
No.
1.1 Study of various Machine Learning tools(Scikit, Get exposure of machine learning
Weka, Matlab) language

1.2 Write a program to implement Linear Regression Understand the actual working of
regression for prediction

1.3 Write a program to implement KNearest Understand the actual working of

Neighbors regression for prediction

1.4 Write a program to implement Random Forest Understand the actual working of
Algorithm classification for label prediction

1.5 Write a program for classification in a data set. Understand the actual working of
classification for label prediction
1.6 Write a program for Automatic grouping of similar Understand the unsupervised
objects into sets technique

1.7 Write a program to implement Genetic Algorithm Learn various GA operators in

solving different types of GA
problems

1.8 Write a program to implement OR, AND gate Understand the mathematical equation and role
using Perceptron with learning rule. of various parameters

Write a program to Implement Back-propagation Understand the mathematical

1.9 algorithm. equation and role of various
parameters

2.0 Case Study – any deep learning application Understand the mathematical
equation and role of various
parameters