M.tech (ML&DS) Syllabus - G

Teerthanker Mahaveer University
Faculty of Engineering
Department of Electronics & Communication Engineering
Study & Evaluation Scheme
of
Master of Technology
(Specialization: Machine Learning & Data Sciences)
[Applicable w.e.f. Academic Session - 2022-23]
[As per CBCS guidelines given by AICTE]
TEERTHANKER MAHAVEER UNIVERSITY

N.H.-24, Delhi Road, Moradabad, Uttar Pradesh-244001
Website: www.tmu.ac.in

M.Tech. (Machine Learning & Data Sciences) w.e.f. Academic Session 2022-23 Page 1
(Established under Govt. of U.P. Act No. 30, 2008)
Delhi Road, Bagarpur, Moradabad(U.P.)
SUMMARY
Institute Name Faculty of Engineering
Master of Technology
Programme (Machine Learning & Data Sciences)
Duration Two-year full time (Four Semesters)
Medium English
Minimum Required Attendance 75%
Credits
Maximum Credits 74
Minimum Credits Required for Degree 74
Assessment:
Evaluation Internal External Total
Theory 40 60 100
Practical/ Dissertations/ Project Reports/ Viva-Voce 50 50 100
Class Test-1 Class Test-2 Assignment(s) Attendance & Total
Participation
10 10 10 10 40
External Internal
Duration of Examination
3 Hours 1.5 Hours
To qualify the course a student is required to secure a minimum of 45% marks in aggregate
including the semester end examination and teachers continuous evaluation (i.e. both internal and
external).A candidate who secures less than 45% of marks in a course shall be deemed to have
failed in that course. The student should have at least 45% marks in aggregate to clear the
semester.
# Policy regarding promoting the students from semester to semester & year to year. No specific
condition to earn the credit for promoting the students from one semester to next semester.
# Maximum no of years required to complete the program: N+2 (N=No of years for program)
Question Paper Structure

The question paper shall consist of six questions. Out of which the first question shall be of short
answer type (not exceeding 50 words) and will be compulsory. Question no. 2 to 6 (from Unit-I to
1
V) shall have explanatory answers (approximately 350 to 400 words) along with having an
internal choice within each unit.
Question No. 1 shall contain 8 parts from all units of the syllabus with at least one question from
2
each unit and students shall have to answer any five, each part will carry 2 marks.
The remaining five questions shall have internal choice within each unit; each question will carry
3
10 marks.
IMPORTANT NOTES:
The purpose of examination should be to assess the Course Outcomes (CO) that will ultimately
lead to the attainment of Programme Specific Outcomes (PSOs). A question paper must assess the
1
following aspects of learning: Remember, Understand, Apply, Analyse, Evaluate & Create
(reference to Bloom’s Taxonomy).
Case Study is essential in every question paper (wherever it is being taught as a part of
2 pedagogy) for evaluating higher-order learning. Not all the courses might have case teaching
methods used as pedagogy.
There shall be continuous evaluation of the student and there will be a provision of a fortnight
3
progress report.
Program Structure- M.Tech (Machine Learning & Data Sciences)
A. Introduction:
High-quality M.Tech education is essential for the digital age. The main aim of this program is to
produce quality professionals and research fellows who can work in every sector of the world by
implementing the technology of computer systems and software. The programme introduces the
various domains of computer science consisting of Artificial Intelligence, Advanced database
management system, advanced data Structure and algorithms, cloud computing, semantic web, Big
Data Analytics. Employability, innovation, theory to practice connectedness is the central focus of the
M.Tech curriculum. The institute emphasis on the following courses balanced with core and elective
courses: The programme structure and credits for M.Tech are finalized based on the stakeholders’
requirements and general structure of the programme However, the minimum number of the credits
for award of M.Tech degree will be 74 credits. Course handout is a thorough teaching plan of a
faculty taking up a course. It is a blueprint which will guide the students about the pedagogical tools
being used at different stages of the syllabus coverage and more specifically the topic-wise complete
plan of discourse, that is, how the faculty members treat each and every topic from the syllabus and
what they want the student to do, as an extra effort, for creating an effective learning. It may be a case
study, a role-play, a classroom exercise, an assignment- home or field, or anything else which is
relevant and which can enhance their learning about that particular concept or topic. Due to limited
availability of time, most relevant topics will have this kind of method in course handout.
Program Course Summary
M.Tech (Machine Learning & Data Sciences) : Two-Years (4-Semester) CBCS Programme
Basic Structure: Distribution of Courses

Total
S.No. Type of Course Credit Hours
Credits
Professional Core
4 Courses of 4 Credit Hrs, (16)
Course
1 4 Courses of 3 Credits Hrs (12) 28
(PCC)
Professional Elective 1 Course of 4 Credits Hrs, (4)

2 Course (PEC) 1 Course of 3 Credits Hrs (3) 7
Laboratory Course
4 Courses of 2 Credits Hrs, (8)
3 (LC) 9
1 Course of 1 Credit Hrs (1)
1 Course of 2 Credit Hrs. (2)
Project/ Seminar/
1 Course of 8 Credit Hrs (8)
4 Dissertation (PROJ)
1 Course of 20 Credit Hrs (20) 30
Total Credits 74
Contact hours include work related to Lecture, Tutorial and Practical (LTP), where our institution will
have flexibility to decide course wise requirements.
B. Choice Based Credit System (CBCS)
Choice Based Credit System (CBCS) is a versatile and flexible option for each student to achieve his
target number of credits as specified by the UGC and adopted by our University. The following is the
course module designed for the M.Tech program:
Professional Core Course (PCC): Professional Core courses of M.Tech program will provide a
holistic approach to master education, giving students an overview of the field, a basis to build and
specialize upon. These core courses are the strong foundation to establish engineering knowledge and
provide broad multi-disciplined knowledge that can be studied further in depth during the elective
phase.
The core courses will provide more practical-based knowledge, case-based lessons and collaborative
learning models. It will train the students to analyze, decide, and lead-rather than merely know-while
creating a common student experience that can foster deep understanding, develop decision-making
ability and contribute to the business and community at large. A wide range of core courses provides
groundwork in the basic engineering disciplines: The integrated foundation is important for students
because it will not only allow them to build upon existing skills, but they can also explore career
options in a range of industries, and expand their understanding of various research fields.
Professional Elective Course (PEC): Professional Elective is an interdisciplinary additional subject
thatis compulsory in the first, second and third semester of a program. The score of Professional
Elective is counted in your overall aggregate marks under Choice Based Credit System (CBCS). Each
Professional Elective paper will be of 7 Credits and students will have the choice of taking PEC’s. We
offer two PEC in semester II and III. Each student has to take Professional Electives from departments
other than the parent department.
Laboratory Courses (LC): A laboratory oriented course which will provide a platform to students to
enhance their practical knowledge and skills by development of small applications/projects. We offer
Laboratory courses in semester I, II and III during the M.Tech program. There will be total 9 credits.
C. Programme Specific Outcomes (PSOs)
The learning and abilities or skills that a student would have developed by the end of two-years.
Understanding and Analyzing the real time problems and to develop solutions by applying
PSO – 1 appropriate mathematical logic and algorithms.
Applying knowledge in various domains to identify research gaps and hence to provide
PSO – 2 solutions to new ideas and innovations.
Applying skills acquired for retrieving, analyzing and managing large data leading to effective
PSO – 3 decision making and application development using suitable engineering tools.
D. Pedagogy & Unique practices adopted: “Pedagogy is the method and practice of teaching,
especially for teaching an academic subject or theoretical concept”. In addition to conventional time-
tested lecture methods, the institute will emphasize on experiential learning. :
1. Case Based Learning:Case based learning enhances student skills at delineating the critical
decision dilemmas faced by organizations, helps in applying concepts, principles and analytical skills
to solve the delineated problems and develops effective templates for business problem solving. Case
method of teaching is used as a critical learning tool for effective learning and we encourage it to the
fullest.
2. Role Play & Simulation: Role-play and simulation are forms of experiential learning. Learners
take on different roles, assuming a profile of a character or personality, and interact and participate in
diverse and complex learning settings. Role-play and simulation function as learning tools for teams
and groups or individuals as they "play" online or face-to-face. They alter the power ratios in teaching
and learning relationships between students and educators, as students learn through their explorations
and the viewpoints of the character or personality they are articulating in the environment. This
student-centered space can enable learner-oriented assessment, where the design of the task is created
for active student learning. Therefore, role-play simulation exercises such as virtual share trading,
marketing simulation etc. are being promoted for the practical-based experiential learning of our
students.
3. Video Based Learning (VBL) & Learning through Movies (LTM): These days technology has
taken a front seat and classrooms are well equipped with equipment and gadgets. Video-based
learning has become an indispensable part of learning. Similarly, students can learn various concepts
through movies. In fact, many teachers give examples from movies during their discourses. Making
students learn few important theoretical concepts through VBL & LTM is a good idea and method.
The learning becomes really interesting and easy as videos add life to concepts and make the learning
engaging and effective. Therefore, our institute is promoting VBL & LTM, wherever possible.
4. Field/Live Projects: The students, who take up experiential projects in companies, where senior
executives with a stake in teaching guide them, drive the learning. All students are encouraged to do
some live projects other than their regular classes.
5. Industrial Visits: Industrial visits are essential to give students hand-on exposure and experience of
how things and processes work in industries. Our institute organizes such visits to enhance students’
exposure to practical learning and work out a report of such a visit relating to their specific topic,
course or even domain.
6. MOOCS: Students may earn credits by passing MOOCs as decided by the college from time to
time. (A) Degree level programmes may be awarded Honors degree provided they earn prerequisite
credits specified by UGC/ Concerned Council. (B) Few theoretical courses (Max 20%) may be
identified by the respective Colleges for On-Line Learning (either Coursera or NPTL). The students
may obtain the certificate of passing such courses from the concerned platform or the colleges may
arrange to conduct exams for such identified courses and (C) A student may earn few extra credits (
shall be considered as audit Courses) by independent Learning through any of the MOOCs Platform,
7. Special Guest Lectures (SGL)): Some topics/concepts need extra attention and efforts as they
either may be high in difficulty level or requires experts from specific industry/domain to make
things/concepts clear for a better understanding from the perspective of the industry. Hence, to cater
to the present needs of industry,we organize such lectures, as part of lecture-series and invite
prominent personalities from academia and industry from time to time to deliver their vital inputs and
provide greater insights.
8. Student Development Programs (SDP): Harnessing and developing the right talent for the right
industry an overall development of a student is required. Apart from the curriculum teaching various
student development programs (training programs) relating to soft skills, interview skills, SAP,
Advanced excel training etc. that may be required as per the need of the student and industry trends,
are conducted across the whole program. Participation in such programs is solicited through
volunteering and consensus.
9. Industry Focused Programs: Establishing collaborations with various industry partners to deliver
the programme on sharing basis. The specific courses/contents are to be delivered by industry experts
to provide practice based insight to the students.
10. Special Assistance Programme for Slow &Fast Learners: After the first class test (CT-1), we
identify the slow learners and the fast learners on the basis of their performance in the class and test.
We counsel the slow learners to assess the knowledge gap and provide them special assistance in
terms of tutorial programmes in learning the subjects or topics. We motivate the fast learners to go
through the various journals and references available in the library and online. We encourage the slow
learners and the fast learners both to read the research papers and after reading them, they write the
research papers with the help of their supervisors to be presented in conferences. We organise at least
one international conference in each semester.
11. Orientation Program: We organize an Orientation Programme for the students to make them well
aware of the rules and regulations of college and university including anti ragging policies.
12. Mentoring Scheme: Every Student shall be provided with a faculty Mentor to help him /her in
their personal & Academic Issues. The mentor maintains a register of al all his/her mentees with
complete personal & parents ‘details. It is essential to have at least one meeting once in a month. The
mentor enters the discussions held, advice given and efforts & improvements made by the mentee.
This register of the mentor must be countersigned by the HOD once a month and by the principal
once in a semester
13. Career & Personal Counselling: We have Training and Placement Cell for Career & Personal
Counselling of the students.
14. Competitive Exam Preparation: Institute provides the foundation for the preparation of
competitive exams. For this, special classes are conducted by the faculty members.
15. Extra-curricular Activities: We organize various extracurricular activities to help students
develop confidence & face the audience with care. It brings out their leadership qualities along with
planning & organizing skills. Students undertake various cultural, sports and other competitive
activities within and outside then campus. This helps them build their wholesome personality.
16. Participation in Workshops, Seminars & writing & Presenting Papers: The purpose of
Workshops, Seminars, and conferences are important for the overall development of the students.
Here the students go through the discussion of a research area/ academic subject with the expert(s).
College conducts at least one Workshop and at least one Seminar. In addition, the College also
conducts one national and one international conference every year. Students actively participated in
Workshops, Seminars & writing & Presenting Papers.
17. Formation of Student Clubs , Membership & Organising And Participating events:: We find
the interest of students and based upon that they are asked to join an existing club or found a new
club. We have various clubs and various events take place among these clubs. The clubs organize
events and participation depends on the nature of the event.
18. Capability Enhancement & Development Schemes: A student may have a wide spectrum of
capabilities hidden inside. We explore the capability of students with the help of various events
throughout the year and find the students with the caliber in a specific field or skill. We then shape the
students by mentoring and providing resources and guidance which is required to make him an Ace of
their field or skill.
19. Library Visit & Utilization of E-Learning Resources: libraries have supported education efforts
by providing teaching resources, information and referral services. A more active approach has been
taken by libraries offering educational classes or one-to-one tutoring programs. Libraries have
outreach programs designed to meet the needs of specific groups of people with limited educational
M.Tech. (Machine Learning & Data Sciences)

Semester I
S. Periods Evaluation Scheme

Category Course Code Course Credit
No L T P Internal External Total
Probabilistic Science for
1 PCC-1 MDS-111 3 1 - 4 40 60 100
Data Analysis
2 PCC-2 MDS-112 Introduction to Data Mining 3 1 - 4 40 60 100
PCC-3 Machine Learning
3 MDS-113 2 1 3 40 60 100
Techniques
PCC-4 Data Visualization and
4 MDS-114 2 1 3 40 60 100
Interpretation
Machine Learning
5 LC-1 MDS-151 - - 4 2 50 50 100
Techniques Lab
Data Visualization and
6 LC-2 MDS-152 - - 4 2 50 50 100
Interpretation Lab
Total 10 4 8 18 260 340 600
M.Tech (Machine Learning & Data Science)
Semester II
S. Periods Evaluation Scheme
Category Course Code Course Credit
No L T P Internal External Total
Introduction to Statistical
1 PCC-5 MDS-211 3 - - 3 40 60 100
Methods
Optimization Methods in
2 PCC-6 MDS-212 3 - - 3 40 60 100
Data Analytics
3 PCC-7 MDS-213 Big Data Analysis 3 - - 4 40 60 100
4 PCE-1 Elective-I 3 - - 3 40 60 100

Introduction to Statistical
5 LC-3 MDS-251 - - 2 1 50 50 100
Methods using R Lab
Industrial Application based
6 LC-4 MDS-252 - - 4 2 50 50 100
Programming using Python
Total 11 2 6 16 260 340 600
Semester III
S. Course Periods Evaluation Scheme
Category Course
No Code L T P Credit Internal External Total
1 PCC-8 MDS-311 Parametric Estimation 3 1 - 4 40 60 100
2 PCE-2 Elective-II 3 1 - 4 40 60 100
Natural Language
3 LC-5 MDS-351 4 2 50 50 100
Processing
Seminar based on
Advanced Industrial
4 PROJ-1 MDS-352 Applications in the field - - 4 2 50 50 100
of Machine Learning
and Data Sciences
Minor Project Based on
Industrial Application
5 PROJ-2 MDS-353 - - - 8 50 50 100
in the field of AI/
ML/DL
Total 6 1 8 20 230 270 500
Semester IV
Periods Evaluation Scheme
S. Course
Category Course Internal External
No Code L T P Credit Total
* *
1 PROJ-3 MDS-451 Dissertation - - - 20 250 250 500
Total - - - 20 250 250 500
ELECTIVE COURSES OFFERED
S. No Code Course L T P Credit
Program Elective I - (Any one)
1 MDS-201 Information Retrieval 3 0 0 3
2 MDS-202 Ethics for Data Science 3 0 0 3
3 MDS-203 Graph Algorithms and Mining 3 0 0 3

Program Elective II - (Any one)
4 MDS-301 Applied Machine Learning 3 1 0 4
MDS-302 Pattern Recognition and Image Processing
5 3 1 0 4
6 MDS-303 Cloud Computing & Network Security 3 1 0 4
M.Tech.- Semester-I L-3
Course
T-1
Code: P-0
MDS-111 Probabilistic Science for Data Analysis
C-4
Course
On completion of the course, the students will be:
Outcomes:
CO1. Understanding the concepts of probability theory
CO2. Understanding the application of random variables in predictions.
Evaluating the mathematical expectation and characteristics of a
CO3.
function
CO4. Applying the methods of standard distributions.
CO5. Implementing the application of probability Theory.
Course
Content:
Probability: Introduction, random experiments, sample space,
events and algebra of events. Definitions of Probability–classical,
Unit-1: 6 Hours
statistical, and axiomatic. Conditional Probability, laws of addition
and multiplication, independent events.
Random variables: discrete and continuous random variables,
p.m.f., p.d.f. and c.d.f., illustrations and properties of random
variables, univariate transformations with illustrations. Two
Unit-2: 6 Hours
dimensional random variables: discrete and continuous type, joint,
marginal and conditional p.m.f, p.d.f., and c.d.f., independence of
variables.
Mathematical Expectation and Generating Functions:
Expectation of single and bivariate random variables and its
Unit-3: 6 Hours
properties. Moments, moment generating function, characteristic
function.
Standard Distributions: Uniform, Binomial, Poisson, geometric,
along with their properties and limiting/approximation cases.
Unit-4: Standard continuous probability distributions: uniform, normal, 6 Hours
exponential, beta and gamma along with their properties and
limiting/approximation cases.
Bayes’theorem and its applications, Least square, Constrain LS,
Unit-5: regressive least square, Minimum Variance Unbiased Estimation, 6 Hours
Uniqueness and inversion theorems along with applications.
1.Probability and Statistics for Data Science, by Carlos Fernandez-
Text Books: Granda.
1.Introduction to Statistical Thought by Michael Lavine.

2.Probability and Statistics for Data Science MATH + R + DATA,
Norman Matloff, CRC Press
Reference
3. Practical Statistics for Data Scientist, Peter Bruce, Andres Bruce
Books:
& Peter Gedeck
4. Mathematical Statistics and Data Analysis – 3 rd Edition, John A.
Rice
Additional
Electronic 1.https://youtu.be/Vfo5le26IhY
reference 2.https://onlinecourses.nptel.ac.in/noc21_ma35/preview
material:
L-3
Course M.Tech.- Semester-I
T-1
Code: Introduction to Data Mining P-0
MDS-112 C-4
Course
Outcomes:
Understanding and applying the concepts of various data warehousing
CO1.
and data mining models.
Understanding and applying the concepts of classification and
CO2.
clustering algorithms.
CO3. Understanding and applying the concepts of Data Cube Technology.
Understanding and applying the concepts of Association Rules in Large
CO4.
Databases
CO5. Applying the concepts of Mining the World Wide Web.
CO6. Applying the concepts of Mining Time-Series and Sequence Data.
Course
Content:
Data warehousing Components, building a Data warehouse, Mapping
the Data Warehouse to a Multiprocessor Architecture, DBMS 6
Unit-1: Schemas for Decision Support, Data Extraction, Clean-up, and Hours
Transformation Tools.
Reporting and Query tools and Applications, Tool Categories, The
Need for Applications, Cognos Impromptu, Online Analytical 6
Unit-2: Processing (OLAP), Multidimensional Data Model, OLAP Hours
Guidelines, Multidimensional versus Multirelational OLAP
Introduction of Data, Types of Data, Data Mining Functionalities,
Interestingness of Patterns – Classification of Data Mining Systems, 6
Unit-3: Data Mining Task Primitives, Integration of a Data Mining System Hours
with a Data Warehouse.
Categorization of Major Clustering Methods, K-means, Partitioning
Methods, Hierarchical Methods, Density-Based Methods, Grid Based 6
Unit-4: Methods, Model-Based Clustering Methods, Constraint, Based Hours
Cluster Analysis, Outlier Analysis.
Mining Frequent Patterns, Associations and Correlations, Mining

Unit-5: Methods,– Mining Various Kinds of Association Rules, Correlation 6
Analysis, Constraint Based Association Mining. Hours
1. Jiawei Han and M Kamber, Data Mining Concepts and Techniques, 2/e,
Text Books:
ElsevierPublishers, 2011.
1. Vipin Kumar, Pang-Ning Tan, Michael Steinbach, Introduction to Data
Reference
Mining,Addison Wesley, 2006.
Books:
2. G Dong, J Pei, Sequence Data Mining, Springer, 2007.
Additional
Electronic 1.https://onlinecourses.nptel.ac.in/noc21_cs06/preview
reference 2.https://youtu.be/ykZ-_UGcYWg
material:
Course L-2
M.Tech.- Semester-I
Code: T-1
MDS-113 Machine Learning Techniques P-0
C-3
Course
On completion of the course, the students will be :
Outcomes:
CO1. Understanding the concepts of Machine Learning principles.
CO2. Analysing the methods of clustering
CO3. Evaluating classification techniques
CO4. Applying the Machine learning algorithms on real time applications.
Course
Content:
Introduction: ML Techniques overview, Validation Techniques
(Cross-Validations), Feature Reduction/Dimensionality reduction
Unit-1: 6 Hours
Principal components analysis (Eigenvalues, Eigen vectors,
Orthogonality)
Clustering: Distance measures, Different clustering methods
(Distance, Density, Hierarchical), Iterative distance-based
Unit-2: 6 Hours
clustering; Dealing with continuous, categorical values in K-Means,
Constructing a hierarchical cluster.
Classification: Naïve Bayes Classifier, Model Assumptions,
Unit-3: Probability estimation, Required data processing, M-estimates, 6 Hours
Feature selection: Mutual information, Classifier
K-Nearest Neighbours: K-Nearest Neighbour algorithm; Wilson
editing and triangulations, Aspects to consider while designing K-
Nearest Neighbour
Unit-4: Support Vector Machines 6 Hours
Linear learning machines and Kernel space, Making Kernels and
working in feature space, SVM for classification and regression
problems
Decision Trees
ID4, C4.5, CART
Ensembles methods
Unit-5: Bagging & boosting and its impact on bias and variance 6 Hours
C5.0 boosting
Random forest
Gradient Boosting Machines and X G Boost
1. Machine Learning for Absolute Beginners A Plain English
Introduction (Machine Learning From Scratch) by Oliver
Theobald.
Text Books: 2. Machine Learning: A Probabilistic Perspective (Adaptive
Computation and Machine Learning series), Kevin P.
Murphy
1. Machine Learning: Tom M. Mitchell

Reference
*Latest editions of all the suggested books are
Books:
recommended.
Course L-2
M.Tech.- Semester-I
Code: T-1
MDS-114 Data Visualization and Interpretation P-0
C-3
Course
Outcomes:
CO1. Understanding the concepts of Visualization design principles.
CO2. Understanding the concepts of Interactive visualization.
CO3. Understanding of Visualization in data science.
CO4. Applying the concept of Data Interpretability
Course
Content:
Introduction: How visualization affects data interpretation, Role of
Unit-1: visualization in data science, Two flavours of data visualization: 6 Hours
exploratory and communicative.
Visualization design principles: Data and task abstraction, best
Unit-2: 6 Hours
practices for encoding, Marks and channels, Tableau assignment
Exploratory Visualization techniques: Handling high-
Unit-3: dimensional data, Comparison techniques, small multiples, handling 6 Hours
uncertainty, Depicting time
Interactive visualization: Why interactivity is needed, handling
multiple views, Brushing and Linking, D3 instructions and
assignments
Unit-4: 6 Hours
Data Interpretability: Causes of misinterpretation, Role of
communicative visualization in sciences, Graphical interpretability:
metrics and approaches.
Visualization in data science: methods and examples, common
Unit-5: machine learning models visualization, Interpretability challenges 6 Hours
and solutions, Transparency and human-machine trust.
1. Visualization Analysis and Design (AK Peters
Visualization Series), Tamara Munzner
Text Books:
2. Interactive Data Visualization for the Web: An
Introduction to Designing with D3 2nd Edition, Scott
Murray.
1. The Visual Display of Quantitative Information, Edward

Reference
Tufte*Latest editions of all the suggested books are
Books:
recommended.
L-0
Course M.Tech.- Semester-I T-0
Code: Machine Learning Technique Lab P-4
MDS 151 C-2
Course
Outcomes:
CO1. Applying and Analyzing various Classification Techniques.
CO2. Applying and Analyzing various Clustering Techniques.
Applying and Analyzing different machine learning techniques for
CO3.
real world problems.
CO4. Applying and Analyzing various Regression Techniques.
CO5. Implementing clustering of patterns
Course Perform the following attributes with the help of python programming for
Content: a given data set.
A. Hello World
1. Data Types: Create and print a numeric and print a numeric.
2. Data Structures: Create and print a vector.
3. Data Frames: Create a data frame.
4. Print a data frame: Index the data frame by row 1 and column 2.
B. Classification
1. Explore the Data
2. Set the working directory
3. Load Iris data
4. Inspect the data
5. Create a color palette
6. Create a scatter plot matrix colored by species
Unit-1:
C. Regression
1. Explore the Data
2. Load Iris data
3. Create scatter plot matrix
4. Load corrgram package
5. Create correlogram
D. Clustering
1. Explore the Data
2. Load Iris data
3. Load color brewer library
4. Create a color palette
5. Create a scatterplot matrix colored by species
L-0
Course M.Tech.- Semester-I T-0
Code: Data Visualization and Interpretation Lab P-4
MDS 152 C-2
Course
Outcomes:
CO1. Applying and Analyzing various chart plotting Techniques.
CO2. Applying and Analyzing various graph plotting Techniques.
CO3. Implementing data tabulation techniques.
CO4. Applying and Analyzing various geospatial graphs.
Applying and Analyzing different visualization of data analytics
CO5.
for real world problems.
Course Visualize the following attributes for given dataset of real time case
Content: studies with the help of data analytics tool (eg. Python Programming).
Plot Chart: Information presented in a tabular, graphical form with

data displayed along two axes. Can be in the form of a graph,
diagram, or map.
Design Table: A set of figures displayed in rows and columns.
Plot Graph: A diagram of points, lines, segments, curves, or areas

that represents certain variables in comparison to each other, usually
along two axes at a right angle.
Plot Geospatial: A visualization that shows data in map form using

different shapes and colors to show the relationship between pieces
of data and specific locations.
Plot Infographic: A combination of visuals and words that

represent data. Usually uses charts or diagrams.
Plot Dashboards: A collection of visualizations and data displayed

in one place to help with analyzing and presenting data.
L-3
Course M.Tech.- Semester-II
T-0
Code: Introduction of Statistical Methods P-0
MDS-211 C-3
Course
Outcomes:
CO1. Understanding the concepts of data analysis.
CO2. Understanding the various hidden features of data variation.
CO3. Applying the various estimator models of feature testing.
CO4. Understanding the basic concepts of multivariate data.
CO5. Understanding the various limitations of data analysis.
Course
Content:
Introduction, Collection and classification of data; different types of
diagrams to represent statistical data; frequency distribution and
Unit-1: 6 Hours
related graphs. Dispersion: Its measure and their uses, Scatter
diagram; Correlation coefficient with its properties and limitations.
Measures of Central Tendency: mathematical and positional.
Measures of Dispersion: range, quartile deviation, mean deviation,
Unit-2: standard deviation, coefficient of variation, Moments, absolute 6 Hours
moments, factorial moments, skewness and kurtosis, Sheppard’s
corrections.
Properties of a good estimate; method of maximum likelihood; tests
Unit-3: of significance; application of chi-square, t, F and Z tests, x charts; 6 Hours
R, p, np and c charts and their uses.
Bivariate data: Definition, scatter diagram, simple, partial and
multiple correlation (3 variables only), rank correlation. Simple
Unit-4: 6 Hours
linear regression, principle of least squares and fitting of
polynomials and exponential curves.
Bias, Minimum Variance Unbiased Estimation(MVUE), Fisher
Information Matrix, Cramer-Rao Lower Bound, Rao Blackwell
Unit-5: 6 Hours
Lehman Sheffe theorem, Best Linear Unbiased Estimators (BLUE),
Maximum Likelihood Estimation(MLE).
1.S. Ross, Introduction to Probability and Statistics for and Engineers and
Scientists, Third Edition, Elsevier, 2004.
Text Books:
2. G. R. Grimmett and D. R. Stirzaker, Probability and Random
Processes, Oxford University Press, 2001
1.R.V. Hogg, J.W. Mckean& A. Craig, Introduction to Mathematical
Statistics, 6th Edition.
2. Montgomery, D. C. and G. C. Runger, Applied Statistics and
Probability for Engineers. 5th Edition. John Wiley & Sons, Inc., NY,
Reference
USA. 2009
Books:
3. Robert H. Shumway and David S. Stoffer, Time Series Analysis and Its
Applications with R Examples, Third edition, Springer Texts in Statistics,
2006.
Additional
1. https://www.digimat.in/nptel/courses/video/111105077/L21.html
Electronic
reference 2. https://youtu.be/GBUMEVcTe-8
material:
Course L-3
M.Tech.- Semester-II
Code: T-0
MDS-212 Optimization Methods in Data Analytics P-0
C-3
Course
Outcomes:
CO1. Understanding the concepts of Smooth Convex Optimization.
CO2. Understanding the various algorithms of convex optimization.
CO3. Understanding the concepts of Nonsmooth Convex Optimization.
CO4. Understanding of Stochastic and Online Optimization.
CO5. Applying the optimization algorithms in machine learning methods.
Course
Content:
Learning under the lenses of optimization, Basics of convex
Unit-1: analysis, Conic programming: LP, SOCP, SDP, Structured 6 Hours
optimization: convexity, smoothness, Separability.
Smooth Convex Optimization: Gradient descent method –
Accelerated gradient descent methods (Nesterov’s method and its
Unit-2: variants) – Projection-free methods (Frank-Wolfe) – Coordinate 6 Hours
descent methods – Applications in logistic regression, matrix
completion.
Non-smooth Convex Optimization: subgradient descent/Mirror
descent – Smoothing techniques – Mirror-Prox method – Primal-
Unit-3: Dual algorithms – Proximal algorithms – Applications in support 6 Hours
vector machines.
Stochastic and Online Optimization: Sample average approximation
– Stochastic approximation (stochastic gradient descent) –
Unit-4: Incremental gradient methods – Online algorithms – Applications in 6 Hours
empirical risk minimization, online learning.
Optimization Perspectives for Selective Topics in Machine
Unit-5: Learning, Sparsity learning, Large-scale kernel machines, common 6 Hours
optimization techniques.
1. Lectures on Convex Optimization (2nd). YuriiNesterov. Springer,
2018.
Text Books: 2. Optimization for Machine Learning. Edited by SuvritSra,
Sebastian Nowozin and Stephen J. Wright. MIT, 2011.
1. Introduction to Optimization. Boris Polyak. Optimization

Reference software, 1987.
Books: 2. Foundations of Optimization. Osman G¨uler. Springer, 2010.
First-Order Methods in Optimization. Amir Beck. SIAM, 2017.
Additional
Electronic https://youtu.be/Ga4WaN__u88
reference
material:
L-3
T-0
Code: Big Data Analysis P-0
MDS-213 C-3
Course
Outcomes:
CO1. Understanding the basic concepts of Hadoop Architecture.
CO2. Understanding the Hadoop Architecture
CO3. Understanding the concepts of Big Data and its importance.
CO4. Understanding the Big data nomenclature.
CO5. Understanding of Predictive Analytics.
Course
Content:
Big Data and its importance, Four Vs, Drivers for Big data,
Unit-1: Introduction to Big data analytics, Big data applications. Algorithms 6 Hours
using Map Reduce.
Introduction to Apache Hadoop & Hadoop Data handling in
Unit-2: Hadoop, Data handling in Map Reduce, Data Serialization. 6 Hours
Hadoop Architecture, Hadoop Storage: HDFS, Common Hadoop

Shell commands, Anatomy of File Write and Read, Name Node,
Unit-3: Secondary Name Node, and Data Node, Hadoop Map Reduce 6 Hours
paradigm, Map and Reduce tasks, Job, Task trackers.
Analytics process model, Analytics model requirements, Types of
data sources, Sampling - types of data elements, Visual Data
Exploration and Exploratory Statistical Analysis, Missing Values,
Unit-4: Outlier Detection and Treatment, Standardizing Data, 6 Hours
Categorization - weights of evidence coding - Variable selection -
Segmentation.
Predictive Analytics: Target Definition - Linear Regression -
Logistic Regression - Decision Trees - Neural Networks - Support
Unit-5: Vector machines - Ensemble Methods - Multiclass Classification 6 Hours
Techniques-Evaluating Predictive Models. Descriptive Analytics,
Sequence Rules.
1. Michael Minelli, Michelle Chambers, and AmbigaDhiraj, "Big Data,
Text Books: Big Analytics: EmergingBusiness Intelligence and Analytic Trends for
Today's Businesses", Wiley, 2013.
1. P. J. Sadalage, M. Fowler, "NoSQL Distilled: A Brief Guide to the
Reference Emerging World of Polyglot Persistence", Addison-Wesley Professional,
Books: 2012.
2. Tom White, "Hadoop: The Definitive Guide", 3/e, O'Reilly, 2012.
Additional
Electronic https://onlinecourses.nptel.ac.in/noc20_cs92/preview
reference https://www.youtube.com/watch?v=bY6ZzQmtOzk
material:
L-3
T-0
Code: Introduction to Statistical Methods using R-Lab P-0
MDS-251 C-3
Course
Outcomes:
CO1. Understanding the basics of R.
CO2. Applying and Analyzing the Linear Regression.
CO3. Applying and Analyzing Logistic Regression, LDA, and KNN.
CO4.
Applying and Analyzing the concepts of Cross-Validation and the
Bootstrap methods.
CO5.
Applying and Analyzing the concepts of Non-linear Modeling such as
Decision Trees.
Course Perform the followings attributes with the help of R Programming
Content: language for given data set.
A. Introduction to R.
B. Linear Regression
1. Simple Linear Regression
2. Multiple Linear Regression
3. Non-linear Transformations of the Predictors
4. Qualitative Predictors
C. Logistic Regression, LDA, and KNN
Unit-1:
D. Cross-Validation and the Bootstrap
1. The Validation Set Approach
2. Leave-One-Out Cross-Validation
3. k-Fold Cross-Validation
4. The Bootstrap
E. Nonlinear Modeling
1. Polynomial Regression and Step Functions
2. Splines
3. Fitting Classification Trees
4. Bagging and Random Forests
M.Tech.- Semester-II L-0
Course
Code: Industrial Application based Programming using T-0
P-4
MDS-252 Python C-2
Course
Outcomes:
CO1. Evaluating the industrial needs and applications
Applying and Analyzing the concept of data analysis in real
CO2.
world problems.
Applying and Analyzing the concept of data visualization in real
CO3.
world problems.
CO4.
Applying and Analyzing the concepts of machine learning and the
Bootstrap methods.
CO5. Implementation, training and deployment of machine learning models
Course
Content:
1. Develop the prototype model with the help of data analytics

and visualization tool for Web Development
and visualization tool for Game Development
and visualization tool for Artificial Intelligence and Machine
Learning
and visualization tool for Desktop GUI
and visualization tool for Image Processing
and visualization tool for Text Processing
and visualization tool for Education Programs and Training
Programs
and visualization tool for Audio and Video Applications
and visualization tool for Data Science and Data Visualization
and visualization tool for Scientific and Numeric Applications
for embedded applications.
L-3
Course M.Tech.- Semester-III
T-1
Code: Parametric Estimation P-0
MDS-311 C-4
Course
Outcomes:
CO1. Understanding the concepts of BVN.
CO2. Understanding the concepts of nonparametric tests.
CO3. Understanding of different types of random vectors.
Understanding the concept of multivariate normal distribution
CO4.
and its properties
CO5. Understanding the concept of empirical distribution function.
CO6. Applying the concept of different type of test methods.
Course
Content:
Bivariate Normal Distribution (BVN): p.d.f. of BVN, properties of
BVN, marginal and conditional p.d.f. of BVN. Multivariate Data:
Unit-1: Random Vector: Probability mass/density functions, Distribution 6 Hours
function, Mean vector & Dispersion matrix, Marginal & Conditional
distributions.
Multivariate Normal distribution and its properties, Sampling
Unit-2: distribution for mean vector and variance- covariance matrix. 6 Hours
Multiple and partial correlation coefficient, and their properties.
Nonparametric Tests: Introduction and Concept, Parametric versus
non-parametric tests, advantages and disadvantages of non-parametric
Unit-3: tests. Test for randomness based on total number of runs, Empirical 6 Hours
distribution function, Kolmogrov Smirnov test for one sample, Sign
tests- one sample.
Kolmogrov Smirnov two samples test, Wilcoxon signed rank tests,
Unit-4: Wilcoxon-Mann- Whitney U test, Kruskal-Wallis test, t-test, 6 Hours
ANOVA.
1. Fundamentals of Statistical Signal Processing. Volume 1: Estimation
Theory, S.M. Kay, Prentice-Hall, 1993.
Text Books:
2. Mathematical Methods and Algorithms for Signal Processing, T.K.
Moon and W.C. Stirling, Prentice-Hall, 2000
1. Joshi Ameet, “Machine learning and artificial intelligence”, Springer
2020.
Reference 2. Jose Unpingco, Python for Probability, Statistics, and Machine Learning,
Books:
second edition, Springer, 2019. 3. Steven W. Knox and Hoboken NJ,
Machine learning: a concise introduction, Wiley 2018.
Additional
Computer
1.https://youtu.be/wt5ASO9PyeU
reference
material:
L-0
Course M.Tech.- Semester-III
T-0
Code: Natural language processing P-4
MDS-351 C-2
Course
Outcomes:
CO1. Understanding the concepts of Natural Language Processing.
CO2. Understanding the concepts of Semantic Roles
Understanding and applying the concept of Finite State Machine
CO3.
Based Morphology and Automatic Morphology Learning
Understanding, applying and analyzing the concept of Rule-Based
CO4.
Machine Translation and Knowledge Based MT System
CO5. Understanding and analyzing the techniques in Speech Recognition.
CO6. Applying the concept of deep learning.
Course
Implement the followings with the help of Data Analytics tool (eg. Python)
Content:
Perform with the help of model creation of:
1 Introduction – Models -and Algorithms - -Regular Expressions, Finite
State Automata, Morphology, Morphological Parsing.
2 Perform with the help of model creation of:
N-grams Models of Syntax - Counting Words - Unsmoothed,
Smoothing, Entropy, Part of Speech Tagging..
Context Free Grammars for English Syntax, Sentence- Level
Constructions, Parsing – Top- down – Early Parsing, feature
Structures – Probabilistic Context-Free Grammars.
Discourse -Reference Resolution - Text Coherence - Discourse
Structure – Coherence, Machine Translation -Transfer Metaphor–
Interlingua- Statistical Approaches.
Applications of Natural Language Processing- Recent Research in
NLP using Deep Learning: Factoid Question Answering, similar
question detection, Dialogue topic tracking, Neural Summarization,
Smart Reply.
1. Daniel Jurafsky, James H Martin, “Speech and Language Processing: An
Reference introduction to Natural Language Processing, Computational Linguistics
Handbook and Speech Recognition”, 2/e,
Prentice Hall, 2008.
Reference 1. C. Manning, H. Schutze, “Foundations of Statistical Natural Language
Material Processing”,MIT Press. Cambridge, MA, 1999.
Course Code: M.Tech- Semester III L-0
MDS-352 SEMINAR T-0
P-4
C-2
Course On completion of the course, the students will be :
Outcomes:
CO1. Understanding the factual knowledge of current areas of research.
Applying gained knowledge in thinking, problem solving, or
CO2.
decisions making process.
CO3. Analyzing problems after doing research literature survey
Analyzing the applicability of modern software tools and
CO4.
technology.
CO5. Creating Seminar Report.
Selection of Topic:
All students pursuing M.Tech shall submit the proposed topic of the
seminar in the first week of the semester to the course coordinator. Care
should be taken that the topic selected does not directly relate to the
subject of the courses being pursued or thesis work, if any. The course
coordinator shall then forward the list to the concerned department
coordinators who will vet the list and add some more topics in consultation
with the faculty of the department. The topics will then be allocated to the
students along with the name of the faculty guide.
Preparation of the Seminar
1 The student shall meet the guide for the necessary guidance for the
seminar work.
2 During the next two to four weeks the student should read the primary
literature germane to the seminar topic. Reading selection should
continuously be informed to the guide.
3 After necessary collection of data and literature survey, the students
must prepare a report. The report shall be arrange in the sequence
consisting of the following: -
a. Top Sheet of transparent plastic.
b. Top cover.
c. Preliminary pages.
(i) Title page
(ii) Certification page.
(iii) Acknowledgment.
(iv) Abstract.
(v) Table of Content.
(vi) List of Figures and Tables.
(vii) Nomenclature.
d. Chapters (Main Material).
e. Appendices, If any.
f. Bibliography/ References.
g. Evaluation Form.
h. Back Cover (Blank sheet).
i. Back Sheet of Plastic (May be opaque or transparent).
4 Top Cover-The sampled top cover shall be as Under:
Title of the seminar
Submitted in Partial fulfillment of the requirement for the degree of
MASTER OF TECHNOLOGY
In
Machine Learning & Data Sciences
by
Name of Student in capital Letters
(Roll No.)
Under the guidance of
GUIDE NAME
Designation
TMU, Moradabad.
DEPARTMENT OF ELECTRONICS & COMMUNICATION

ENGINEERING
FACULTY OF ENGINEERING
N.H. 24, BAGARPUR,
MORADABAD-244001
MONTH AND YEAR
5 Title Page: The Sampled title page shall be as under:
Title of the seminar
Submitted in Partial fulfillment of the requirement for the degree of
MASTER OF TECHNOLOGY
In
Machine Learning & Data Sciences
by
Name of Student in capital Letters
(Roll No.)
Under the guidance of
GUIDE NAME
Designation,
TMU, Moradabad.

ENGINEERING
N.H. 24, BAGARPUR,
MORADABAD-244001
MONTH AND YEAR
6 Certification page:- This shall be as under
ENGINEERING
N.H. 24, BAGARPUR,
MORADABAD-244001
MONTH AND YEAR The seminar Report and Title “Topic of the
Seminar.” Submitted by Mr. /Ms. (Name of the student) (Roll No.) may be
accepted for being evaluated
Date Signature
Place (Name of guide)
For GuideIf you Choose not to sign the acceptance certificate above,
please indicate reasonsfor the
same from amongst those given below:
i) The amount of time and effort put in by the student is not sufficient;
ii) The amount of work put in by the student is not adequate;
iii) The report does not represent the actual work that was done / expected
to be done;
iv) Any other objection (Please elaborate)
7 Acknowledgement:- This shall be as under
I am highly thankful to the almighty who gave me the strength and
health for completing my seminar.It gives me pleasure to express my
thanks and gratitude to my seminar guide Guide Name who gave me
the opportunity to do this seminar. His/Her guidance and support
helped me to complete my seminar.
I would like to thanks Principal Sir ……, HOD……. and my course
coordinator …….. for their motivation and encouragement.
I am also thankful to everyone who has helped me in making this
report. I am really thankful to them. Their encouragement really helped
me to frame this seminar in a better manner. I also, whole heartedly,
thank my parents and friends for their support and helpfulness.
Place: Moradabad Name of the Student

8 Abstract- A portion of the seminar evaluation will be based on the
abstract. The abstract will be evaluated according to the adherence to
related technical fieldand according to the format described below.
The marking shall be as follows.
Internal: 50 Marks
By The Faculty Guide - 25 Marks
By Committee Appointed By the Director – 25 Marks
External: 50 Marks
By External Examiner Appointed By the University – 50 Marks
The seminar abstract is an important record of the coverage of your topic and provides a valuable
source of leading references for students. Accordingly, the abstract must serve as an introduction
to your seminar topic. The abstract will be limited to 500 words, excluding figures and tables (if
any). The abstract will include references to the research articles upon which the seminar is based
as well as research articles that have served as key background material.
Course Code: M.Tech- Semester III L-0
MDS-353 Minor Project Based on Industrial Application in the T-0
field of AI/ ML/DL P-16
C-8
Course On completion of the course, the students will be:
Outcomes:
Understanding the phases of SDLC and performing initial
CO1.
investigation about project.
Understanding to design entity relationship diagram and data flow
CO2.
diagram of the project.
CO3. Applying the designing procedures to design database.
Developing software requirements specification Document for the
CO4.
project.
CO5. Developing Forms and Front end of the Project.
Description
Students should devote themselves to prepare something tangible,
which could be a working model of their thoughts based on their
subject of choice (Preferably based on AI/ML/DL).
The project shall be completed and submitted at least one month
before the last teaching day of the III semester, date of which shall be
notified in the academic calendar.
The assessment of performance of students should be made at least
twice in the semester. In this semester student shall present the final
project live as also using overheads project or power point presentation
on LCD to the internal committee as also the external examiner.
The evaluation committee shall consist of faculty members constituted
by the college which would comprise of at-least three members
comprising of the Department Coordinator, Class Coordinator and a
nominee of the Director. The students guide would be a special invitee
to the presentation. The seminar session shall be an open house
session. The internal marks would be the average of the marks given
by each member of the committee separately in a sealed envelope to
the Principal.
Internal: 50 Marks
By The Faculty Guide - 25 Marks
External: 50 Marks
*Format of the Report should be followed as per the current
recent modification made by the University
This will be made available to the candidate through various
information flow medium.
Course Code: M.Tech- Semester IV L-0
MDS-451 Dissertation T-0
P-40
C-20
Course On completion of the course, the students will be:
Outcomes:
Understanding to design entity relationship diagram and data flow
CO1.
diagram of the project
Evaluating the real time issues and solution gaps in existing
CO2.
industrial applications.
CO3. Applying the designing procedures to design database.
Applying software or hardware requirements specification for the
CO4.
project.
Applying the concepts of Machine Learning and Data sciences in
CO5.
real world applications.
Description
Students should devote themselves to prepare something tangible,
which could be a working model of their thoughts based on their
subject of choice (Preferably based on Machine Learning and Data
Sciences).
The project shall be completed and submitted at least one month
before the last teaching day of the III semester, date of which shall be
notified in the academic calendar.
The assessment of performance of students should be made at least
twice in the semester. In this semester student shall present the final
project live as also using overheads project or power point presentation
on LCD to the internal committee as also the external examiner.
The evaluation committee shall consist of faculty members constituted
by the college which would comprise of at-least three members
comprising of the Department Coordinator, Class Coordinator and a
nominee of the Director. The students guide would be a special invitee
to the presentation. The seminar session shall be an open house
session. The internal marks would be the average of the marks given
by each member of the committee separately in a sealed envelope to
the principal.
Internal: 250 Marks
By The Faculty Guide -125 Marks
External: 250 Marks
*Format of the Report should be followed as per the current
recent modification made by the University
This will be made available to the candidate through various
information flow medium.
Program Electives-I
L-3
T-1
Code: Information Retrieval P-0
MDS-201 C-4
Course
Outcomes:
CO1. Understanding the information retrieval system.
CO2. Understanding Cataloguing and Indexing.
CO3. Understanding the automatic Indexing methodology.
CO4. Understanding the User Search Algorithms.
CO5. Understanding the Text Search Algorithms.
Course
Content:
Introduction to Information Retrieval Systems, Information Retrieval System,
Objectives of Information Retrieval Systems, Functional Overview,
Unit-1: Relationship to Database Management Systems, Digital Libraries and Data 6 Hours
Warehouses. Capabilities of Information Retrieval System.
Cataloguing and Indexing: History and Objectives of Indexing, Indexing
Process, Automatic Indexing, Information Extraction Data Structure:
Unit-2: Introduction to Data Structure, Stemming Algorithms, Inverted File Structure, 6 Hours
N-Gram Data Structures, PAT Data Structure, Signature File Structure,
Hypertext and XML Data Structures.
Automatic Indexing: Classes of Automatic Indexing, Statistical Indexing,

Natural Language, Concept Indexing, Hypertext Linkages Document and
Unit-3: Term Clustering: Introduction to Clustering, Thesaurus Generation, Item 6 Hours
Clustering, Hierarchy of Clusters.
User Search Techniques: Search Statements and Binding, Similarity Measures

and Ranking, Relevance Feedback, Selective Dissemination of Information
Unit-4: Search, Weighted Searches of Boolean Systems, Searching the INTERNET 6 Hours
and Hypertext Information, Introduction to Information Visualization,
Cognition and Perception.
Text Search Algorithms: Introduction to Text Search Techniques, Software
Text Search Algorithms, Hardware Text Search Systems. Multimedia
Unit-5: 6 Hours
Information Retrieval: Spoken Language Audio Retrieval, Non-Speech Audio
Retrieval, Graph Retrieval, Imagery Retrieval.
1.Christopher D. Manning, PrabhakarRaghavan, HinrichSchutze, Introduction

Text Books: to Information Retrieval‖, Cambridge University Press, First South Asian
Edition, 2008.
1. Implementing and Evaluating Search Engines‖, The MIT Press, Cambridge,

Massachusetts London, England, 2010
2. Ricardo Baeza – Yates, BerthierRibeiro – Neto, ―Modern Information
Reference
Retrieval: The concepts and Technology behind Search‖ (ACM Press Books),
Books:
Second Edition, 2011.
3. Stefan Buttcher, Charles L. A. Clarke, Gordon V. Cormack, ―Information
Retrieval
Additional 1.https://nptel.ac.in/courses/106101007
Electronic 2.https://youtube/fFxpSmyICwI
reference
material:
L-3
T-1
Code: Ethics for Data Science P-0
MDS-202 C-4
Course
Outcomes:
CO1. Understanding the ethical issues for data science.
CO2. Understanding the concepts of Research ethics for data science.
CO3. Understanding the concepts of Discrimination and algorithms.
CO4. Understanding the impact of Data ethics in social life.
CO5. Understanding of Privacy and Surveillance.
Course
Content:
Overview of ethical issues in data-driven organizations: Overview
of data science as an ethical practice, Introduction to the unique
Unit-1: ethical challenges of ‘big data’, Ethical Theory - Philosophical 6 Hours
frameworks for assessing fairness, Early theories of fairness,
Moving towards contemporary theories of fairness.
Research ethics for data science: Ethical side effects of the publish
or perish system: p-hacking and small sample size, The
misapplication of informed consent in data veillance practices.
Unit-2: Techniques of data ethics: Getting from data to individuals: Internet 6 Hours
traces and Geo fingerprints. All data are human data: On the
discriminatory trouble with training data.
Discrimination and algorithms: The ethics of price discrimination,
Criminal justice by algorithm. The philosophical challenge of
Unit-3: thinking in categories-How humans explain their social worlds 6 Hours
through perceptions and statistics.
Social processes and the impact of categorical life. Data ethics for
researchers Health Research, Educational Research, The ethics of
Unit-4: data scraping and storage, Mosaic data, found data, and designed 6 Hours
data.
Privacy and Surveillance, Special topics in surveillance: Adtech,

Unit-5: Special topics in surveillance: Employment, Differential privacy.. 6 Hours
1. Ethics and Data Science, by DJ Patil, Hilary Mason, and Mike

Text Books: Loukides, 25 July 2018.
Reference 1.Ethics for the Information Age (Links to an external site.), 7th Ed., by
Books: Michael Quinn
Additional
Electronic 1.https://youtu.be/gLHMhCtxEYE
reference
material:
L-3
T-1
Code: Graphs-Algorithms and mining P-0
MDS-203 C-4
Course
Outcomes:
CO1. Understanding the graph theory and graph mining foundations
CO2. Analysing the graph mining methods,
CO3. Analysing the concepts of graph mining in real time problems,
Applying graph mining algorithms to analyze large-scale datasets
CO4.
on various domains
Course
Content:
Introduction to graphs: Introduction to graphs and basic
terminology, Representations of a graph, types of graphs, basic
Unit-1: algorithms for decomposing graphs into parts, connectivity of 6 Hours
graphs, matching on graphs.
Graph algorithms: Graph colouring, graphs on surface, directed
graphs, Shortest path algorithms, algorithms to discover minimum
Unit-2: spanning tree, Flows in Networks and some important flow 6 Hours
algorithms, Searching Graphs and Related algorithms.
Graph Mining: Motivation for Graph Mining, Applications of
Graph Mining, Mining Frequent Subgraphs –Transactions,
BFS/Apriori Approach (FSG and others), DFS Approach (gSpan
Unit-3: and others), Diagonal and Greedy Approaches, Constraint-based 6 Hours
mining and new algorithms, Mining Frequent Subgraphs, graph
visualizations.
Applications of Graph Mining: Web mining, centrality analysis,
Link analysis algorithms, graph clustering and community
Unit-4: detection, Node classification and Link prediction, Influential 6 Hours
spreaders, Influence maximization, Geo-social and location based
networks
1.Diestel, R. (2010).Graph Theory, 4th ed.Springer-Verlag, Heidelberg
2. J. Han and M. Kamber, Data minining–Concepts and Techniques,
Text Books:
2ndEdition, Morgan kaufmanPublishers, 2006
1.Bing Liu, Web Data Mining: Exploring Hyperlinks, Contents, and

Usage Data, Springer publishing, 2009
Reference 2. Jure Leskovec, AnandRajaraman, Jeff Ullman. Mining of Massive
Books: Datasets. Book 2nd edition. Cambridge University Press
3. David Easley and Jon Kleinberg. Networks, Crowds, and Markets.
Cambridge University Press, 2010.
Additional
Electronic 1. https://youtu.be/rPed_1sUO7s
reference 2. https://youtu.be/KoG5lEAJmgI
material:
Program Elective -II
L-3
Course
Applied Machine Learning T-1
Code: P-0
301 C-4
Course
Outcomes:
CO1. Applying and Analyzing the techniques of Python programming.
CO2. Applying and Analyzing the methods of Data Visualization.
CO3. Applying and Analyzing of process of exploratory data analysis
Applying the concept of machine learning algorithm in real world
CO4.
applications
CO5. Understanding the case studies of industry applications
Course
Content:
Fundamental of Programming: Python for Data Science
Unit-1: Introduction, Data Structures, Functions, Numpy, Matplotlib, 6 Hours
Pandas, Computational Complexity
Exploratory Data Analysis and Data Visualization
Plotting for exploratory data analysis (EDA), Linear Algebra,
Probability and Statistics, Interview Questions on Probability and
Unit-2: 6 Hours
statistics, Dimensionality reduction and Visualization,
PCA(principal component analysis), (t-SNE)T-distributed
Stochastic Neighbourhood Embedding, Dimensionality Reduction
Plotting for exploratory data analysis (EDA)
Linear Algebra, Probability and Statistics, Interview Questions on
Unit-3: Probability and statistics, Dimensionality reduction and 6 Hours
Visualization: PCA(principal component analysis), (t-SNE)T-
distributed Stochastic Neighbourhood Embedding
Real world problem: Predict rating given product reviews on
Amazon, Classification And Regression Models: K-Nearest
Unit-4: Neighbors, K-NN(K Nearest Neighbour), Classification algorithms 6 Hours
in various situations, Performance measurement of models,
Performance Measurement Models.
Case Studies(based on real time other case studies can be
replaced)
Case Study 1:Quora question Pair Similarity Problem
Unit-5: Case Study 2:Facebook Friend Recommendation 6 Hours
Case study 3:Taxi demand prediction
Case study 4: Stackoverflow tag predictor
Case Study 5: Spam Detection
Text Books: 1. Advanced Research Computing by University of oxford
Reference 1. Latest Reserach Publications (WoS/Scopus)

Books: *Latest editions of all the suggested books are recommended.
L-3
Course M.Tech.
T-1
Code: Pattern Recognition and Image Processing P-0
302 C-4
Course
Outcomes:
CO1. Understanding the concepts of Image Processing.
CO2. Understanding the concepts of Image Restoration.
CO3. Understanding of Segmentation Techniques.
CO4. Applying the concept of pattern recognition
CO5. Evaluating statistical parameters of images
Course
Content:
Introduction to Image Processing
Image formation, image geometry perspective and other
Unit-1: transformation, stereo imaging elements of visual perception. 6 Hours
Digital Image-sampling and quantization serial & parallel Image
processing.
Image Restoration
Image Restoration-Constrained and unconstrained restoration
Wiener filter , motion blur remover, geometric and radiometric
Unit-2: 6 Hours
correction Image data compression-Huffman and other codes
transform compression, predictive compression two tone Image
compression, block coding, run length coding, and contour coding.
Segmentation Techniques
Segmentation Techniques-thresh holding approaches, region
Unit-3: 6 Hours
growing, relaxation, line and edge detection approaches, edge
linking, supervised and unsupervised classification techniques.
Pattern Recognition
Basics of pattern recognition, Design principles of pattern
recognition system, Learning and adaptation, Pattern recognition
Unit-4: 6 Hours
approaches, Mathematical foundations – Linear algebra, Probability
Theory, Expectation, mean and covariance, Normal distribution,
multivariate normal densities, Chi squared test.
Statistical Patten Recognition
Bayesian Decision Theory, Classifiers, Normal density and
discriminant functions, Parameter estimation methods: Maximum-
Unit-5: 6 Hours
Likelihood estimation, Bayesian Parameter estimation, Dimension
reduction methods – Principal Component Analysis (PCA), Fisher
Linear discriminant analysis, Expectation-maximization (EM).
2. Digital Image Processing – Ganzalez and Wood, Addison Wesley,
Text Books:
1993.
2. Fundamental of Image Processing – Anil K.Jain, Prentice Hall of
Reference India.
Books:
*Latest editions of all the suggested books are recommended.
Course L-3
M.Tech.-
Code: T-1
303 Cloud Computing & Network Security P-0
C-4
Course
Outcomes:
CO1. Understanding the concepts of Cloud Computing.
CO2. Understanding the concepts of Virtualization.
Analysing the impact of of Building Cloud in industrial
CO3.
applications.
CO4. Evaluating the parameters of the cloud security.
CO5. Analysing the business and commercial model of cloud computing
Course
Content:
Introduction to Cloud Computing: What is cloud? ,Services
provided by cloud are categorized :Software As a Service(SaaS)
,Infrastructure As a Service(IaaS) ,Platform As a Service(PaaS)
Unit-1: 6 Hours
,Desktop As a Service (DaaS) and VDI etc. How Cloud Computing
Works, Advantages & Disadvantages, Applications for Businesses
Cloud Service Providers
Brief overview:Major Cloud Service providers – Amazon AWS,
Unit-2: Google App Engine, Microsoft, VMware. How Companies are 6 Hours
using Cloud Computing Cloud Computing Risks and Issues.
Virtualization:Concepts, Objectives, Types of Virtualization & its
benefits, Introduction to Various Virtualization OS (Hypervisor),
Unit-3: HA/DR using Virtualization Live Migration of VMs, SAN backend 6 Hours
concepts, S/W defined Networking (OpenFlow/OpenVSwitch),
S/W Defined Data center, S/W Defined Storages.
Building Cloud: Networks Designing and Implementing a Data
Center-Based Cloud, Industry and International Standards
Unit-4: 6 Hours
Communication Requirements for Cloud Implementation, Private ,
Public & Hybrid Clouds
Cloud Security: Infrastructure Security, Network level security,
Unit-5: Host level security, Application level security, Data security and 6 Hours
Storage, Data privacy and security Issues.
1. Cloud Computing from Beginning to End by Ray J Rafaels
Text Books:
1. Cloud Computing for Dummies by Judith S. Hurwitz, Robin Bloor,

Reference Marcia Kaufman, Fern Halper
Books: 2. Cloud Computing: Concepts, Technology & Architecture by Zaigham
Mahmood, Ricardo Puttini, Thomas Erl

M.tech (ML&DS) Syllabus - G

Uploaded by

Copyright:

Available Formats

M.tech (ML&DS) Syllabus - G

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

M.tech (ML&DS) Syllabus - G

Uploaded by

Copyright:

Available Formats

Teerthanker Mahaveer University

Study & Evaluation Scheme

TEERTHANKER MAHAVEER UNIVERSITY

TEERTHANKER MAHAVEER UNIVERSITY

Question Paper Structure

Basic Structure: Distribution of Courses

Professional Elective 1 Course of 4 Credits Hrs, (4)

M.Tech. (Machine Learning & Data Sciences)

S. Periods Evaluation Scheme

M.Tech (Machine Learning & Data Science)

4 PCE-1 Elective-I 3 - - 3 40 60 100

2 PCE-2 Elective-II 3 1 - 4 40 60 100

M.Tech (Machine Learning & Data Science)

Total - - - 20 250 250 500

2 MDS-202 Ethics for Data Science 3 0 0 3

3 MDS-203 Graph Algorithms and Mining 3 0 0 3

6 MDS-303 Cloud Computing & Network Security 3 1 0 4

1.Introduction to Statistical Thought by Michael Lavine.

Mining Frequent Patterns, Associations and Correlations, Mining

1. Machine Learning: Tom M. Mitchell

1. The Visual Display of Quantitative Information, Edward

Plot Chart: Information presented in a tabular, graphical form with

Design Table: A set of figures displayed in rows and columns.

Plot Graph: A diagram of points, lines, segments, curves, or areas

Plot Geospatial: A visualization that shows data in map form using

Plot Infographic: A combination of visuals and words that

Plot Dashboards: A collection of visualizations and data displayed

1. Introduction to Optimization. Boris Polyak. Optimization

Hadoop Architecture, Hadoop Storage: HDFS, Common Hadoop

C. Logistic Regression, LDA, and KNN

1. Develop the prototype model with the help of data analytics

DEPARTMENT OF ELECTRONICS & COMMUNICATION

DEPARTMENT OF ELECTRONICS & COMMUNICATION

Place: Moradabad Name of the Student

Automatic Indexing: Classes of Automatic Indexing, Statistical Indexing,

User Search Techniques: Search Statements and Binding, Similarity Measures

1.Christopher D. Manning, PrabhakarRaghavan, HinrichSchutze, Introduction

1. Implementing and Evaluating Search Engines‖, The MIT Press, Cambridge,

Privacy and Surveillance, Special topics in surveillance: Adtech,

1. Ethics and Data Science, by DJ Patil, Hilary Mason, and Mike

1.Bing Liu, Web Data Mining: Exploring Hyperlinks, Contents, and

Text Books: 1. Advanced Research Computing by University of oxford

Reference 1. Latest Reserach Publications (WoS/Scopus)

1. Cloud Computing for Dummies by Judith S. Hurwitz, Robin Bloor,

You might also like