S.Y.M.Sc.

(Data Science) Pattern 2019

Deccan Education Society’s

FERGUSSON COLLEGE (AUTONOMOUS),
PUNE

Syllabus
for

S. Y. M. Sc. (Data Science)

[Pattern 2019]
(S.Y. M.Sc. Semester-III and Semester-IV)

From Academic Year

2020-21

1 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

Deccan Education Society’s

Fergusson College (Autonomous), Pune

S.Y.M.Sc. Data Science (Pattern 2019)

From academic year 2020-21

Particulars Name of Paper Title of Paper No. of

Paper Code Credits
S.Y. M.Sc. Paper - 1 CSD5301 Optimization Techniques 4
Semester III
Paper - 2 CSD5302 Emerging Trends in Data Science 4

Paper - 3 CSD5303 Deep Learning 4

CSD5304 Data Science Case Studies OR

Paper - 4 CSD5305 Artificial Intelligence OR 4

CSD5306 MOOC-II

Paper - 5 CSD5307 Data Science Practical – V(Deep 4

Learning )

Paper - 6 CSD5308 Data Science Practical – VI ( Project ) 4

S.Y. M.Sc. Paper - 1 CSD5401 Industrial Training 8

Semester IV

2 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper -1 (CSD5301): Paper title:Optimization Techniques
[Credits-4]

Course Outcomes
At the end of this course, students will be able to
CO1 Finding stationary points and locating local minima and local maxima of given
single variable and multivariable functions
CO2 Solving Linear programming problems, IPP and learning the tools and techniques of
quantitative analysis. Identify the real life problem for which a linear and dynamic
optimization model is developed.
CO3 To develop those parts of the optimization theory that apply for linear and Network
models.
CO4 Learning various optimization techniques and gaining knowledge to optimize
hyperparameters since it is a key issue in a machine learning algorithm.

Unit Details Lectures

I Classical optimization techniques [10]
1.1 Maxima,Minima, critical points of singlevariable functions and
multivariable functions
1.2 Single variable optimization with and without constraints, multi –
variable optimization with and without constraints, method of
Penalty methods, Lagrange multipliers
1.3 Kuhn-Tucker conditions

II Linear programming [15]

2.1 Application of Simplex method
2.2 Two-phase method
2.3 Big-M method, Duality
2.4 Integer linear Programming
2.5 Sensitivity analysis. Assignment problem: Hungarian’s Algorithm,
Degeneracy, applications, Unbalanced problem.
2.6 Traveling salesman problem

III CPM/PERT [8]

3.1 Simulation of CPM/PERT network
3.2 Analysis of an activity network
3.3 Simulation of inventory system and manufacturing System
IV Hyperparameter optimization [15]
4.1 Gradient of a function.
4.2 Steepest descent method
4.3 Nelder Mead’s Simplex search method
4.4 Newton’s method.

3 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

Books
1. Frederick Hillier and Mark Hillier, Introduction to Management Science, McGraw-Hill,
6th Edition, 2018
2. Eric Walter, Numerical Methods and Optimization: A Consumer Guide, Springer
Cham,2014
3. Taha, H.A., Operations Research: An Introduction, Prentice Hall of India, 9th Edition,
2010
4. L.S.Srinath, PERT and CPM Principles and Applications, Affiliated East-West Press
(Pvt.) Ltd, 3rd edition, 2001
5. S.S. Rao, Optimization Theory and Applications, Wiley Eastern Ltd, 2nd Edition, 1984

Web References
1. Mathematical Foundation of Data Analysis. J .Phillips –
Download link: http://www.cs.utah.edu/~jeffp/M4D/M4D-v0.6.pdf

4 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper -2 (CSD5302): Paper title:Emerging Trends in Data Science
[Credits-4]

Course Outcomes
At the end of this course, students will be able to
CO1 Use advanced data science methods and tools
CO2 To leverage statistical sciences, machine learning technologies and industry-specific
datasets
CO3 to implement unique data models that can solvechallenging problems across all
industries

Unit Details Lectures

I Introduction [15]
1.1 Data science Concept
1.2 Different Methodology
1.3 Cloud and Data Science
1.4 Data Preparation, Data Transformation
1.5 Data visual representation
1.6 Machine learning Concept and algorithm
II Technology Used in Data Science [18]
2.1 Technology Implementation method with data
2.2 Exploring and Preparing auto data
2.3 Validating automotive data
2.4 Visualize preliminary data wrangling results
2.5 Run summary statistics on the results
2.6 Exploring visualization tool for data
2.7 Implementation of ML concept
III Various Domain based Case study implementation with technology [15]

Books
1. AI Sweigart, Automate the Boaring Stuff with Python, November 2019
2. Jeff Leek , The Elements of Data Analytic Style, Leanpub publications , published on
2015-03-02
3. Roger D. Peng and Elizabeth Matsui , The Art of Data Science , Leanpub publications.
2015 - 2016
4. Advice and Insights from 25 Amazing Data Scientists ,The Data Science Handbook,
Leanpub publications. 2015 – 2016

5 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

5. Shai Shalev-Shwartz and Shai Ben-David, Understanding Machine Learning: From

Theory to Algorithms c 2014.

Web References
1. https://www.packtpub.com/in/data/complete-data-wrangling-and-data-visualization-in-r-
video
2. https://www.edureka.co/blog/importance-data-science-cloud-
computing/#:~:text=Data%20science%20and%20cloud%20computing,a%20need%20for%20
Data%20Scientists.

6 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper - 3 (CSD5303): Paper title:Deep Learning
[Credits-4]
Course Outcomes
At the end of this course, students will be able to
CO1 To understand basics of deep learning
CO2 To study the architecture of deep neural networks.
CO3 Study various tools required for deep learning
CO4 Hands on to study deep neural networks in real life applications

Unit Details Lectures

I Foundations of Neural Network and Deep Learning [5]
1.1Introduction to deep learning
1.2Neural Network Basics
1.3Artificial neural network and its layers
1.4Necessary activation functions
1.5Notion of Partial and total Derivatives and functions
1.6Weights and weight sharing, loss function, partial ordering
II Deep Learning Networks [7]
2.1 Working with Tensorflow, Keras ,Pytorch
2.2 Backpropagation in Feed-forward Networks
2.3 Feed Forward for Classification and Regression

III Improving the Deep Neural Networks [8]

3.1 Regularization: L1, L2, Dropout
3.2 Early Stopping
3.3 Optimization for Training Deep Models
3.4 Hyperparameter Tuning

IV Convolutional Neural Networks [8]

4.1 Introduction to Convolutional Networks
4.2 Understanding Convolution and Pooling
4.3 Different Classic CNN Architectures
4.4 CNN with MNIST Dataset and also with other datasets
4.5 Application of CNN in Computer Vision: Image Classification,
Object detection

V Recurrent Neural Networks [8]

5.1 The Sequential Problem
5.2 The RNN Model
5.3 The LSTM Model
5.4 Application of RNN in NLP and Time Series Forecasting
VI Restricted Boltzmann Machines (RBM) [8]
6.1 Introduction to RBMs

7 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

6.2 Training RBMs

6.3 RBM MNIST
6.4 Collaborative Filtering With RBM
6.5 Application of RBM in Recommender Systems

VII Autoencoders [4]

7.1 Introduction to Autoencoders
7.2 Application of Autoencoders in Recommender Systems and Image
Processing

Books
1. Nikhil Baruma, Fundamentals of Deep Learning, O’Reilly publication, 2019.
2. Seth Weidman, Deep Leaning from Scratch-Building with Python from First Principal,
O’Reilly publication, 2019.
3. Bharat Ramsundar, Peter Eastman, Patrik Walters, Vijay Pnade, Deep Learning for the
Life Sciences, O’Reilly publication, 2019.
4. SudharsanRavichandiran, Hands-on Deep Learning Algorithms with Python, Packt
Publication 2019.
5. Christopher Bishop, Pattern Recognition and Machine Learning, Springer. 2006. [CB-
2006].
6. Duda, R.O., Hart, P.E., and Stork, D.G. Pattern Classi cation. Wiley-Interscience. 2nd
Edition. 2001.
7. Hastie, T., Tibshirani, R. and Friedman, J. The Elements of Statistical Learning. Springer.
2001.
8. Bishop, C. M. Neural Networks for Pattern Recognition. Oxford University Press. 1995.
9. Ian Goodfelllow, YoshuaBenjio, Aaron Courville, Deep Learning, The MIT Press
10. Aggarwal, Charu C., “Neural Networks and Deep Learning”, Springer International
Publishing, 1st Edition.

Web references
1. www.deeplearning.ai
2. www.tensorflow.org

8 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper - 4 (CSD5304): Paper title:Data Science Case Studies
[Credits-4]
Course Outcomes
At the end of this course, students will be able to
CO1 Solve a real business problem statement in a particular domain.
CO2 Have hands on experience of working on prevalent Data Science tools.
CO3 Deliver a comprehensive end to end project

Unit Details Lectures

I Brief Introduction to Data Science [4]
1.1 What is Data Science
1.2 Why Now? - The importance of Data Science in today’s business
environment.
1.3 Difference between Data Science, Business Intelligence and Data
Analysis
1.4 Real World Applications of Data Science
1.5 Popular Tools and Languages to Apply Data Science
1.6 A Typical Data Science Team
1.7 Team Structures

II Brushing Up on your MS Excel Skills [6]

2.1 Basic Functions
2.2 Advanced Functions
2.3 Sorting, Filtering and Pivot tables
2.4 Charts and other visualization tools
2.5 Handling Date formats for time series analysis
2.6 Short Cut Keys
2.7 Making simple Dashboards

III Making Data Work for You! [4]

3.1 What can Data do?
3.2 Types of Data
3.3 Data Exploration
3.4 Data Sources and Risks
3.5 Data Cleaning
3.6 Manipulating Time Series Data
3.7 Data Storage and Retrieval

IV Analysis, Prediction and Visualization [4]

4.1 Generating Charts and plots to better understand the
4.2 output
4.3 Interpretation
4.4 Prediction

9 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

4.5 Conclusion

V Communicate Results [4]

5.1 Creating Dashboards in Tableau
5.2 Creating a Story in Tableau
5.3 Creating Dashboards in MS Excel
5.4 Generate High End Presentations in MS PowerPoint

VI The Data Science Workflow [2]

6.1 Understand the steps in the life cycle of a Data Science project
6.2 Theoretical Vs Applied Data Science

VII Case Study [24]

7.1 Problem Statement – Domain and scope of the study
7.2 Data Source
7.3 Data Preparation
7.4 Choice of Model
7.5 Model Building
7.6 Type of tools to use
7.7 Analysis
7.8 Presentation

Books
1. Microsoft Excel Data Analysis and Business Modeling, By Wayne L. Winston, Published
by Microsoft Press 2019
1. Ryan Sleeper, Practical Tableau, O’Reilly publication, 2019.
2. Python Data Science Hand Book -
https://tanthiamhuat.files.wordpress.com/2018/04/pythondatasciencehandbook.pdf

10 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper - 4 (CSD5305): Paper title:Artificial Intelligence
[Credits-4]
Course Outcomes
At the end of this course, students will be able to
CO1 Present an overview of artificial intelligence (AI) principles and approaches
CO2 Develop a basic understanding of the building blocks of AI
CO3 Apply AI techniques to different real world problems and games

Unit Details Lectures

I Introduction to Artificial Intelligence [4]
1.1 What is AI? Early work in AI
1.2 AI and related fields
1.3 AI problems and Techniques

II Problems, Problem Spaces and Search [8]

2.1 Defining AI problems as a State Space Search: examples
2.2 Production Systems
2.3 Search and Control Strategies
2.4 Problem Characteristics
2.5 Issues in Design of Search Programs
2.6 Additional Problems

III Heuristic Search Techniques [8]

3.1 Generate-and-test
3.2 Hill Climbing
3.3 Best First Search
3.4 Problem Reduction
3.5 Constraint Satisfaction
3.6 Mean-Ends Analysis

IV Knowledge Representation [8]

4.1 Representations and Mappings
4.2 Approaches to Knowledge Representation
4.3 Knowledge representation method
4.4 Propositional Logic
4.5 Predicate logic
4.6 Representing Simple facts in Logic
4.7 Representing Instances and Is-a relationships
4.8 Computable Functions and Predicates
4.9 Resolution
4.10 Forward and backward chaining

V Slot – and – Filler Structures [8]

5.1 Weak Structures

11 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

5.2 Semantic Networks

5.3 Frames
5.4 Strong Structures
5.5 Conceptual Dependencies

VI Game Playing [6]

6.1 Minimax Search Procedures
6.2 Adding alpha-beta cutoffs
6.3 Uncertainty Reasoning: Basic Probability Axioms, Baye's Rule,
Baysian Classification, Certainty Factor Theory, Dempster Shafar
Theory

VII Learning [6]

7.1 What is learning?
7.2 Rote Learning
7.3 Learning by taking advice
7.4 Learning in problem solving
7.5 Learning from examples
7.6 Explanation based learning

Books
1. Elaine Rich and Kevin Knight, Artificial Intelligence, Tata McGraw Hill, 3rd Edition,
2008
2. Dan Patterson, Introduction to Artificial Intelligence and Expert System, Prentice Hall of
India Pvt. Ltd., 2nd Edition, 1990

12 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper - 5 (CSD5307): Paper title:Data Science Practical – V( Deep Learning )
[Credits-4]
Course Outcomes
At the end of this course, students will be able to
CO1 To be familiar with basics of deep learning concepts
CO2 Hands on with various neural networks
CO3 Working with applications based on deep neural networks.
CO4 Handling real time case studies in deep learning

List of practical (Compulsory 10 + 2 Activity)

1 Deep Learning using Keras

2 Deep Learning using Pytorch
3 Deep Learning using Tensorflow
4 Application of CNN in Computer Vision
5 CNN in Image Classification
6 CNN in Object Detection
7 Application of RNN in NLP
8 RNN in Time Series Forecasting
9 Application of RBM in Recommender Systems
10 Case Study

Books
1. SudharsanRavichandiran, Hands-on Deep Learning Algorithms with Python, Packt
Publication, 2019
2. Ian Goodfelllow, YoshuaBenjio, Aaron Courville, Deep Learning, The MIT Press

Web Reference
1. www.deeplearning.ai
2. www.tensorflow.org

13 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester III

Subject: Data Science
Paper - 6 (CSD5308): Paper title: Data Science Practical – VI (Project)
[Credits-4]
Course Outcomes
At the end of this course, students will be able to
CO1 Understand the software development life cycle of Data Science project.
CO2 Define problem statement and build complete solution to a specific problem.
CO3 Use different tools and techniques for solving problem and representing analysis.

Objective:
The Objective of project is to make the students understand life cycle of data
science project. Students should be able to define a problem statement, collect
data and process it and explore the avenues in data science modeling (e.g.
Predictive).

The Project can be platform, language and technology independent. Project will be evaluated
by project guide. Assessment will be done weekly in the respective batch. Evaluation will be
on the basis of weekly progress of project work, progress report, oral, results and
documentation and demonstration.

You should fill your status of the project work on the progress report and get the Signature of
project guide regularly. Progress report should sharply focus how much time you have spent
on specific task. (The format of progress report is given as follow.) You should keep all
signed progress report. Project will not be accepted if progress report is not submitted and all
responsibility remains with student.

Project Progress Report

Roll No and Name of the Student

Title of the project

Project guide name

Sr. No From Date To Date Details of Project work Project guide sign
(with date)

14 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

15 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

Deccan Education Society’s

FERGUSSON COLLEGE (AUTONOMOUS),
PUNE

Syllabus
for

S. Y. M. Sc. (Data Science)

[Pattern 2019]
(S.Y. M.Sc. Semester-IV)

From Academic Year

2020-21

16 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

S.Y. M.Sc. Semester IV

Subject: Data Science
Paper - 1 (CSD5401): Paper title: Industrial Training
[Credits-8]
Course Outcomes
At the end of this course, students will be able to
CO1 Get an insight into the actual work culture of the I.T. industry.
CO2 Make the students aware of the skills and technologies needed to work in the I.T.
industry.
CO3 Understand different ways to approach a problem and build solution.

Duration: Minimum 3 months

The necessary details for Industrial Training course are as follows:

A student can complete Industrial Training Project (ITP) in any I.T. industry / academic
institute / with a research project of a teacher / an expert funded by any funding agency for a
minimum period of three months.

1. There will be a teacher coordinator for a group of 10 students. A teacher coordinator

is responsible to:

▪ Maintain a weekly status / progress report of the student.

▪ Keep in touch with the reporting authorities from industry for each student.
▪ Help the students to solve their difficulties.
▪ Arrange the meeting and presentations as per requirement.
▪ Guide each student for preparing final project report.
▪ Keep complete documentation record for each student separately.
▪ Internal assessment of each student for 50 marks.

The workload for this teacher coordinator is proposed as four hours per week.

The workload for a teacher coordinator who is guiding 3 students doing their ITP in
Fergusson College (Autonomous) Pune (no mentor from industry) is proposed as four hours
per week.

2. Guidelines for submitting the final project report

The student must include the project completion certificate issued by the respective industry
/research institute/educational institute in the report. A student will submit two hard bound
copies and one CD: Student Copy, Department copy, CoE copy of the work carried out
during ITP (CD to be given by students).

3. Scheme of Assessment:

▪ Continuous Internal Assessment

17 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

Evaluation for internal 50 Marks will be done by the Internal Teacher Coordinator.

Description Marks

Weekly Reports (Minimum 12) 30

Final Project Report writing 10

Presentation Demo 10

▪ End Semester Assessment

Evaluation for external 50 Marks will be done by a panel of three consisting of One
Industrial Expert, One Academic Expert (External from other college) and One Internal
Examiner. Each examiner is expected to assess each student for 50 marks independently
and average of the three scores is to be considered as the final ESE score (out of 50)

Description Marks

Knowledge and Execution of the System 15

Final Project Report 15

Presentation 10

Viva 10

▪ The internal examiner(s) will be responsible for submitting the total marks out of 100 to
examination section.
▪ The final grade (to be printed on the mark list) is to be calculated on the basis of UGC 10
point scale.

Marks Grade Grade Point

90 – 100 O: Outstanding 10

80-89 A+: Excellent 9

70-79 A: Very Good 8

65-69 B+: Good 7

60 - 64 B: Above Average 6

55-59 C+: Average 5

18 Department of Computer Science, Fergusson College (Autonomous), Pune

 S.Y.M.Sc. (Data Science) Pattern 2019

50 -54 C: Below Average 4

45-49 D: Satisfactory 3

40-44 E:Pass 2

0 -39 F: Fail 0

Absent 0

Note:- A student who has obtained Grade F will have to carry out this project once again for
a complete semester (minimum three months).

19 Department of Computer Science, Fergusson College (Autonomous), Pune