Applied Statistics and Data Science

Master's programme

Educational plan

Type:
Master
Speciality:
056201.04.7 - Statistics
Specialisation:
056201.04.7 - Applied statistics and data science
Qualification awarded:
Master of Statistics
Programme academic year:
2025/2026
Mode of study:
Full time
Language of study:
Հայերեն

General educational component

Chair code Name of the course Credits
1st semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ01
1. Purpose of the Course
· introduce students to the basics of the Python programming language.
· To learn to work with data, variables, arrays, functions.
· Develop skills that will allow students to design solutions to non-trivial problems using Python.
· To enable students to use the basics of object oriented programming.
2. Educational Outcomes
a. professional knowledge and expertise
1. Present the structure of the Python language, basic grammar, variable types.
2. Use the basics of object-oriented programming.
b. practical professional skills
3. Write computer programs using the Python programming language.
4. Implement various algorithms using the Python programming language.
5. Use the Numpy package in calculations.
3. Description
· introduce students to the basics of the Python programming language.
· To learn to work with data, variables, arrays, functions.
· Develop skills that will allow students to design solutions to non-trivial problems using Python.
· To enable students to use the basics of object oriented programming.
4. Teaching and Learning Styles and Methods
1. Presentation with Power point materials.
2. Practical works in computer classrooms.
5. Evaluation Methods and Criteria
The test is conducted by questionnaires with a maximum value of 20 points. Students who get 10 or more points from the test in the 20-point system will be considered to have passed the test.
6. Basic Bibliography
  • Python Crash Course. A Hands-On, Project-Based Introduction to Programming 1st Edition by Eric Matthes, 2015.
  • A. Shaw, Learn Python The Hard Way third edition 2014.
  • Wesley J. Chun Core Python Programming, Second edition 2009.
  • Wes McKinney, Python for Data Analysis, Third edition 2014.
7. Main sections of the course
· Python language: Introduction
· Data types
· Boolean operations
· Cycles
· Functions
· Numpy
· Object Oriented Programming
1st semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ02
1. Purpose of the Course
● acquaint students with data storage and management systems,
● enable students to design and build databases using modern technologies,
● acquaint students with SQL-language and DBMS packages.
2. Educational Outcomes
a. professional knowledge and expertise
1. describe the processes of physical and logical database design and database modeling,
2. use the basic concepts of DBMS,
b. practical professional skills
3. to design databases,
c. generic/transferable skills
4. write queries and perform analyzes using the capabilities of the SQL language.
3. Description
● acquaint students with data storage and management systems,
● enable students to design and build databases using modern technologies,
● acquaint students with SQL-language and DBMS packages.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical work using computer programs,
3. individual work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Database system concepts. Silberschatz, Abraham, Henry F. Korth, and S Sudarshan. 6th ed., 2010.
  • Fundamentals of Database Systems, 6th ed., Elmasri & Navathe, Addison-Wesley, 2011.
  • Thomas Connolly and Carolyn Begg, "Database Systems, A Practical Approach to Design, Implementation, and Management", Addison Wesley, Fourth Ed. 2001.
  • An Introduction to Database Systems, by CJ Date, Addison-Wesley, 2003.
7. Main sections of the course
● the database system,
● Entity-Relationship Data Model,
● relations, algebra of relations,
● norming databases, normal forms,
● Structured SQL query language. Composition of queries,
● indexing,
● query processing, optimization,
● Object-oriented databases: NoSQL & MongoDB
1st semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
1603/Մ03
1. Purpose of the Course
· To develop English communication skills based on a professional speech patterns used in the field,
· to form the necessary abilities in all manifestations of speech (reading, listening, writing and speaking) deepening knowledge of basic vocabulary,
· introduce the strategy and principles of professional writing.
2. Educational Outcomes
a. professional knowledge and expertise
1. apply knowledge of a foreign (English) language to the extent necessary to extract information of a professional nature from foreign language sources,
b. practical professional skills
2. will have knowledge of general and professional vocabulary in a foreign (English) language to the extent necessary for professional communication, as well as for reading and translating texts,
c. generic/transferable skills
3. will be able to compose a clear, well-structured text on a professional topic in a foreign language, describe his experience and events, present justifications for his own opinions and goals.
3. Description
· To develop English communication skills based on a professional speech patterns used in the field,
· to form the necessary abilities in all manifestations of speech (reading, listening, writing and speaking) deepening knowledge of basic vocabulary,
· introduce the strategy and principles of professional writing.
4. Teaching and Learning Styles and Methods
· Collaborative Learning,
· Problem based method
· Spaced Learning,
· "World Cafe"
· Flipped classroom method
· case based method
· Inquiry Based Learning.
5. Evaluation Methods and Criteria
Test.
Evaluation methods:
Progress assessment, "Portfolio" assessment/Portfolio assessment, Language skills assessment/Proficiency assessment).
Criteria:
Check past professional topics, chat on professional topics, check mandatory assignments.
6. Basic Bibliography
  • Maier-Fairclough J. & Butzphal G. Career Express Business English (C1). Reading UK: Garnet Publishing Ltd., 2012.
  • MacKenzie I. Professional English in Use / Finance. Cambridge: Cambridge University Press, 2010.
  • The Intensive course for the Senior Students of the Institute of Mathematics, Economics & Mechanics, OA Rumyanceva, 2015.
  • Oxford English for Information Technology, Eric H. Glendinning, John McEwan, 2006.
  • Master P. English Grammar and Technical Writing. US, 2004.
  • Linville L. Academic Skills Achievement Program. Boston: IRWIN Mirror Press, 1994.
  • Other necessary materials
  • Podcasts:
  • Eslgold.com
  • BBC: The English we speak - english-we-speak
  • FluentU
  • TEDx Talks
7. Main sections of the course
· Preliminary familiarization with topics (eg breakout room activity, brainstorming)
· Presenting the material itself (eg reading a jigsaw puzzle, listening to or playing a video);
· Analysis stage (e.g.: message and act of the material being read or listened to. Vocabulary. Analysis, Mindmapping),
· Synthesis phase (e.g., after analysis, brainstorming, formation and expression of opinions, positions using new and accumulated knowledge),
· Self-assessment of perceived material (eg: Survey/Mentimeeter, Mindmapping),
· of the topic ( e.g.: presentation )
· Formative assessment of Progress, Self/Peer assessment,
· assessment.
1st semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
1604/Մ03
1. Purpose of the Course
· deepen and improve as much as possible all language skills (reading-understanding-reproducing, listening-understanding-reproducing, speaking, writing),
· to develop the skills and abilities to communicate in German,
· deepen general and professional language vocabulary, grammar and stylistic characteristics knowledge.
2. Educational Outcomes
a. professional knowledge and expertise
1. create professional and general communicative texts monologues and dialogues,
2. distinguish the inconsistencies of the mother tongue and the studied foreign language, to understand the means of their transfer in both languages,
3. define all layers of professional vocabulary with the aim of their precise use,
4. present and interpret professional viewpoints and arguments, formulate, compose, justify personal opinion, discuss, debate current issues of profession,
b. practical professional skills
5. while listening or reading the text, take notes for later use in writing, logically and clearly constructing the essay,
6. to build a verbally connected speech describing phenomena, events, justifying one's point of view,
c. generic/transferable skills
7. effectively use various information sources (including the Internet) to gather, critically analyze and present information.
Upon successful completion of the course, the student's knowledge and abilities must correspond to the level A2-B1 of the Pan-European Framework of Reference for Languages (CEFR).
3. Description
· deepen and improve as much as possible all language skills (reading-understanding-reproducing, listening-understanding-reproducing, speaking, writing),
· to develop the skills and abilities to communicate in German,
· deepen general and professional language vocabulary, grammar and stylistic characteristics knowledge.
4. Teaching and Learning Styles and Methods
1. practical training under the guidance of a lecturer,
2. individual and group work,
3. individual and team research work,
4. independent work
5. oral presentation (realization of an individual independent project),
6. written and oral examination/questionnaire,
7. discussion of situational problems.
5. Evaluation Methods and Criteria
The course ends with a test. It tests the material passed, taking into account the degree of acquisition and reproduction of basic general and professional vocabulary, as well as the basic patterns characteristic to German.
6. Basic Bibliography
  • DaF kompakt neu A1 - B1. Klett Verlag Stuttgart, 2016.
  • Meltonjan G., Soghomonjan K., Diwanjan N. Deutsch (für Stufen A2-B1). Jerewan, Verlag der Universität Jerewan, 2022.
  • Gabrieljan J. u. a., Praktische deutsche Grammatik, Jerewan, 2017.
7. Main sections of the course
1. Grammar. the main morphological and syntactic structures and types, their features in speech and professional field.
2. Lexical, grammatical and stylistic peculiarities of the professional language of the given field.
3. The analysis of professional texts and their realization in German / written and spoken/.
1st semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
1705/Մ03
1. Purpose of the Course
· to develop students' language skills and communication abilities in all areas of linguistic activity,
· ensure the application of the language knowledge and skills students already gained for professional purposes,
· expand the vocabulary of the professional language, deepen the knowledge about the morphological, syntactic and stylistic features of the professional language.
2. Educational Outcomes
a. professional knowledge and expertise
1. demonstrate in-depth knowledge of professional language vocabulary,
2. demonstrate knowledge of basics of creating professional text summaries,
b. practical professional skills
3. analyze the listened/read professional text, separating the main content from the secondary content, independently compose a text on a professional topic,
4. to prepare abstracts, reports, summaries of scientific texts on professional topics,
c. generic/transferable skills
5. to expand the possibilities of receiving information from Russian-language sources,
6. discuss and analyze professional issues in Russian.
3. Description
· to develop students' language skills and communication abilities in all areas of linguistic activity,
· ensure the application of the language knowledge and skills students already gained for professional purposes,
· expand the vocabulary of the professional language, deepen the knowledge about the morphological, syntactic and stylistic features of the professional language.
4. Teaching and Learning Styles and Methods
· practical training
· independent work
· team work,
· oral presentation
· written and oral quizzes.
5. Evaluation Methods and Criteria
The course ends with an oral exam based on the results of the final written exam at the end of the semester.
6. Basic Bibliography
  • Амиантова Э.И. Лексика русского языка. Сборник упражнений. Москва, Наука, 2006.
  • Аникина М.А. Синтаксис сложноподчиненного предложения, Москва, Русский язык, 2000.
  • Балыхина Т.М. Формы работы над учебным текстом по специальности// Методические рекомендации к обучению учебно-профессиональному общению студентов-иностранцев и специалистов в вузах нефилологического профиля, Донецк, 1990.
  • Демидова А.К. Пособие по русскому языку. Научный стиль речи. Оформление научной работы, Москва, Русский язык, 1991.
  • Ласкарева Е.Р. Чистая грамматика, СПБ, Златоуст, 2006.
  • Хавронина С.А, Клобукова Л.П, Михалкина И.В. Курс для деловых людей, Москва, ПАИМС, 1993.
7. Main sections of the course
· Features of general scientific and narrow professional terminology
· Ideological features of scientific style
· The syntactic structures specific to the scientific style
· Means of expressing different semantic connections in a scientific text
· A concise and comprehensive presentation of a professional text
· Genres of scientific style: abstract, report, article, summary
· The principles of writing essays, reports, summaries
1st semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
MANDATORY
1608/Մ03
1. Purpose of the Course
· To develop abilities of perception and interpretation of scientific texts
· To introduce different aspects of scientific French at different levels (phonetic - tonal, verbal morphological-syntactic, stylistic),
· To develop scientific communication abilities.
2. Educational Outcomes
a. professional knowledge and expertise
1. to discuss linguistic and stylistic aspects of various scientific texts,
2. to describe linguistic terminology related to different problems,
b. practical professional skills
3. perform an analysis of the communicative potential of scientific texts,
4. translace in practice different scientific texts from French to Armenian and viceversa
c. general/transferable skills
5. use of information from variety of sources (online resources, scientific articles and etc),
6. apply the obtained knowledge also for other adjacent disciplines, within the framework of the study program.
3. Description
· To develop abilities of perception and interpretation of scientific texts
· To introduce different aspects of scientific French at different levels (phonetic - tonal, verbal morphological-syntactic, stylistic),
· To develop scientific communication abilities.
4. Teaching and Learning Styles and Methods
practical classes, reading of the assigned literature, discussions, independent research work, group work, innovative methods of teaching: communicative, interactive, etc
5. Evaluation Methods and Criteria
The course ends with a pass/no pass test.
6. Basic Bibliography
  • Parizet, M.L., E. Grandef, M. Corsain Collection activités pour le cadre commun. Activités pour le cadre européen commun de référence. B. 1. ClE International, 2006.
  • Boulares, M., J.L. Frerot Grammaire progressive du francais Niveau avancé. ClE International, 2004.
7. Main sections of the course
Scientific style: characteristic features, genre features, sub-styles. Morphological-syntactic features of a scientific French language. Norm patterns of the scientific language. Basic principles of vocabulary classification in French. The main ways of vocabulary enrichment. An analysis of linguistic features of various scientific texts.

Professional educational component

Chair code Name of the course Credits
1st semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
MANDATORY
0105/Մ04
1. Purpose of the Course
● to acquaint students with theoretical and numerical methods of optimization, in particular, the theory of unconstrained and constrained finite-dimensional smooth optimization and numerical solution algorithms, elements of linear and convex programming.
2. Educational Outcomes
a. professional knowledge and expertise
1. classify optimization problems,
2. study the questions of the existence and uniqueness of extremes, to check necessary and sufficient conditions for extremes,
3. construct the dual linear programming problem,
b. practical professional skills
4. use numerical methods to find extremum points of multivariate functions (with or without constraints),
5. formulate various applied problems as linear programming problems,
6. use numerical algorithms to solve linear programming problems,
c. generic/transferable skills
7. work with literature, work in a team.
3. Description
● to acquaint students with theoretical and numerical methods of optimization, in particular, the theory of unconstrained and constrained finite-dimensional smooth optimization and numerical solution algorithms, elements of linear and convex programming.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical exercises,
3. implementation of a group project.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Stephen Boyd and Lieven Vandenberghe, Convex Optimization, Cambridge University Press, available online at .
  • Edwin KP Chong, Stanislaw H. Zak, An Introduction to Optimization, 4th Ed, Volume 76 of Wiley Series in Discrete Mathematics and Optimization, John Wiley & Sons, 2013.
  • Jorge Nocedal, Stephen J. Wright, Numerical Optimization, Springer, 2006.
7. Main sections of the course
● Convex sets and functions,
● Finite dimensional unconstrained optimization,
● Numerical methods for finite dimensional unconstrained optimization problems,
● Finite dimensional constrained optimization,
● Numerical methods for finite dimensional constrained optimization problems,
● Linear programming, duality, solution algorithms.
1st semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
MANDATORY
0105/Մ05
1. Purpose of the Course
● introduce students to modern econometric models and tools,
● introduce regression analysis, estimation of coefficients and study of their properties.
2. Educational Outcomes
a. professional knowledge and expertise
1. perform regression analysis with spatial data (cross-sectional data),
2. perform regression analysis with time series data,
3. explore regression properties, test hypotheses,
b. practical professional skills
4. choose a model,
5. perform regression analysis using computer packages,
6. perform modeling and forecasting of the correlation of economic data of different nature.
3. Description
● introduce students to modern econometric models and tools,
● introduce regression analysis, estimation of coefficients and study of their properties.
4. Teaching and Learning Styles and Methods
1. theoretical lectures,
2. practical exercises.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Individual work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Jeffrey Wooldridge, Introductory Econometrics, A Modern Approach, 5th edition, Cengage Learning, 2012 .
  • William Greene, Econometric Analysis, 7th Ed ., Pearson, 2012 .
  • James Stock, Mark Watson, Introduction to Econometrics, 3rd Ed ., Addison-Wesley, 2010 .
  • Магнус Я.Р., Катышев П.К., Пересецкий А.А., Эконометрика,6-ое издание, Москва,«Дело», 2004.
7. Main sections of the course
● simple regression,
● multiple regression,
● properties of regression coefficients, hypothesis testing,
● multicollinearity, dummy variables, heteroskedasticity,
● regression analysis with time series,
● Logit and Probit models.
1st semester
Contact hours - 4 hours per week
Lecture - 4 hours/week, individual work - 8 hours/week
MANDATORY
0105/Մ06
1. Purpose of the Course
to teach the concepts of mathematical analysis, linear algebra, probability theory, and numerical analysis that are necessary in statistics, optimization, and machine learning courses.
2. Educational Outcomes
a. professional knowledge and understanding
1. find local and global extrema,
2. calculate the statistical properties of random variables,
b. practical professional skills
3. reduce the dimensionality of the data using PCA,
4. approximate data with GMM,
c. general/transferable skills
5. use various sources of information.
3. Description
to teach the concepts of mathematical analysis, linear algebra, probability theory, and numerical analysis that are necessary in statistics, optimization, and machine learning courses.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work,
2. individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam: presentation of a research paper with a maximum value of 4 points (20%).
3. Quizzes with a total maximum value of 3 points (15%).
4. Final exam with a maximum value of 9 points (45%).
6. Basic Bibliography
  • Calculus, 7th Ed, by James Stewart, 2012.
  • Linear Algebra: A Modern Introduction, Fourth Edition, by David Poole, 2014.
  • Probability Theory: The Logic of Science 1st Edition by E. T. Jaynes, 2003.
  • M. Deisenroth, A. Faisal, and C. Ong., Mathematics for Machine Learning, Cambridge University Press, (2020).
7. Main sections of the course
1. elements of mathematical analysis (partial derivatives, gradient, chain rule, extrema),
2. elements of linear algebra (solving SLE using Gauss's method, -1-trick, projection operators, Cholesky decomposition, SVD, least squares problem),
3. elements of probability theory (Random variables and their statistical properties, common probability distributions),
4. numerical analysis (PCA, GMM, EM algorithms).
1st semester
Contact hours - 4 hours/week
Lecture-4 hours/week, Individual work-8 hours/week
MANDATORY
0105/Մ07
1. Purpose of the Course
▪ describe classical statistical models and methods,
▪ teach the basics of the R programming language,
▪ teach the implementation of statistical models in R.
2. Educational Outcomes
a . professional knowledge and expertise
1. choose appropriate statistical models for various practical problems,
2. recognize the basic commands of R,
3. describe the statistical model solution algorithm in R,
b . practical professional skills
4. create programs in R,
5. build statistical models for various applied problems,
6. solve specific application problems with the help of R
3. Description
▪ describe classical statistical models and methods,
▪ teach the basics of the R programming language,
▪ teach the implementation of statistical models in R.
4. Teaching and Learning Styles and Methods
1. Theoretical lectures, practical work with computers.
2. Completion of individual/group assignments.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam: presentation of a research paper with a maximum value of 4 points (20%).
3. Quizzes with a total maximum value of 4 points (20%).
4. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Larry Wasserman, All of Statistics. A Concise Course in Statistical Inference, Springer Texts in Statistics, Springer, 2003.
  • Jay Devore , Kenneth N. Berk, Matthew Carlton Modern Mathematical Statistics with Applications (Third Edition), Springer, 2021
  • George Casella, Roger Berger, Statistical Inference (Second Edition) , Duxbury, 2002.
  • Peter Dalgaard, Introductory Statistics With R, 2nd Ed, Springer, 2008.
7. Main sections of the course
● R programming language.
● Descriptive statistics.
● Point and interval estimation.
● Statistical hypothesis testing.
● Non-parametric hypotheses.
● Basic statistical distributions in R.
● Modeling and usage of basic statistical quantities and methods in R.
2nd semester
Contact hours - 2 hours per week
Lecture - 2 hours/week, individual work - 4 hours/week
MANDATORY
0105/Մ09
1. Purpose of the Course
· to introduce the basic concepts and methods of data processing,
· to develop skills for solving practical problems using modern programs of data processing.
2. Educational Outcomes
a. professional knowledge and understanding
1. introduce concepts, modern methods and models of data analysis,
b. practical professional skills
2. use the algorithms of data analysis in practical problems,
3. to classify and cluster data collected from different fields,
4. make predictions based on data analysis,
c. general/transferable skills
5. use professional literature and other sources of information,
6. conduct research using knowledge of data analysis.
3. Description
· to introduce the basic concepts and methods of data processing,
· to develop skills for solving practical problems using modern programs of data processing.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical exercises,
3. implementation of a group project.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Han, J., Kamber, M., & Pei, J. (2011). Data mining: Concepts and techniques (3rd ed.). Waltham: Morgan Kaufmann.
  • Ian H. Witten and Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques (Second Edition), Morgan Kaufmann, 2005.
  • Hand, Mannila, and Smyth. Principles of Data Mining. Cambridge, MA: MIT Press, 2001.
7. Main sections of the course
● Introduction to data analysis.
● Data preparation.
● Presentation of data analysis knowledge.
● Feature-oriented analysis.
● Algorithms of data analysis: classification and prediction.
2nd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ10
1. Purpose of the Course
● to equip students with advanced programming knowledge,
● Familiarize students with testing, error handling and debugging,
● Familiarize students with various Python libraries and packages.
2. Educational Outcomes
a. professional knowledge and expertise
1. formulate the principle of parallel computing,
2. use basics of functional programming,
b. practical professional skills
3. write relatively complex and systematic computer programs,
4. to apply error handling and debugging,
5. to implement the principle of parallel computing in Python,
6. to use various Python libraries.
3. Description
● to equip students with advanced programming knowledge,
● Familiarize students with testing, error handling and debugging,
● Familiarize students with various Python libraries and packages.
4. Teaching and Learning Styles and Methods
1. Slide presentations,
2. practical work using computer programs,
3. independent work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Tests with a total maximum value of 6 points (30%).
4. Independent work with a maximum value of 6 points (30%).
6. Basic Bibliography
  • Python Crash Course. A Hands-On, Project-Based Introduction to Programming 1st Edition by Eric Matthes, 2015.
  • Shaw, Learn Python The Hard Way third edition 2014.
  • Wesley J. Chun Core Python Programming, Second edition 2009.
  • Wes McKinney, Python for Data Analysis, Third edition 2014.
7. Main sections of the course
● Error handling.
● Debugging.
● Testing.
● Functional programming.
● Libraries.
● The principle of parallel calculations.
2nd semester
Contact hours - 4 hours/week
Lecture - 4 hours/week, individual work - 8 hours/week
MANDATORY
0105/Մ11
1. Purpose of the Course
▪ To describe the Bayesian approach to statistical problems in data analysis,
▪ To give an idea about prior distribution, likelihood and posterior distribution,
▪ To teach how to build Bayesian networks and perform Bayesian data analysis.
2. Educational Outcomes
a. professional knowledge and expertise
1. perform Bayesian estimation in various statistical problems,
2. build Bayesian networks,
b. practical professional skills
3. perform Bayesian data analysis, model selection and evaluation,
4. solve specific application problems of data analysis with the help of computer packages,
c. generic/transferable skills
5. analyze existing problems, propose mathematical models, ways of solving them.
3. Description
▪ To describe the Bayesian approach to statistical problems in data analysis,
▪ To give an idea about prior distribution, likelihood and posterior distribution,
▪ To teach how to build Bayesian networks and perform Bayesian data analysis.
4. Teaching and Learning Styles and Methods
- Theoretical lectures, practical work with computers.
- Completion of individual/group assignments.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Tests with a maximum value of 4 points (20%).
4. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • William Bolstad, James Curran, Introduction to Bayesian Statistics, 3rd Ed ., Wiley, 2017.
  • Peter Lee, Bayesian Statistics, an introduction, Wiley, 2012.
  • Jean-Michel Marin, Christian P. Robert, Bayesian Essentials with R, 2nd Ed, Springer, 2014.
  • Peter Congdon, Applied Bayesian Modelling, Wiley, 2014.
  • Andrew Gelman, John Carlin et al, Bayesian Data Analysis, 3rd Ed ., CRC Press, 2014.
  • Allen B. Downey, Think Bayes, O'Reilly, 2013.
  • Adnan Darwiche, Modeling and Reasoning with Bayesian Networks, CUP, 2009.
7. Main sections of the course
● Bayesian estimation for discrete random variables
● Bayesian estimation for the normal distribution
● A Bayesian approach to hypothesis testing
● Bayesian estimation for regression
● Hierarchical models
● Bayes Networks
● Bayesian nonparametric estimation
● Numerical Bayesian methods
2nd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ12
1. Purpose of the Course
● to acquaint students with the main methods of time series analysis and forecasting with them,
● to introduce students to specialized computer programs and their application to perform time series analysis.
2. Educational Outcomes
a. professional knowledge and expertise
1. describe the main characteristics of time series,
2. apply ARMA models for time series analysis and use these methods in practice,
3. use the elements of spectral analysis,
b. practical professional skills
4. build various application models using time series,
5. use probabilistic, optimization, statistical, econometric, numerical and other mathematical methods to investigate developed models,
6. use a professional software to solve resulting problems,
c. generic/transferable skills
7. analyze existing problems of the field and propose approaches to solve them.
3. Description
● to acquaint students with the main methods of time series analysis and forecasting with them,
● to introduce students to specialized computer programs and their application to perform time series analysis.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical work using computer programs,
3. independent work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Tests with a total maximum value of 6 points (30%).
4. Independent work with a maximum value of 6 points (30%).
6. Basic Bibliography
  • JD Hamilton, Time Series Analysis, Princeton, 1994.
  • Robert H. Shumway, David S. Stoffer, Time Series Analysis and Its Applications, With R Examples, 4 th Ed., Springer 2017.
  • Peter J. Brockwell, Richard A. Davis, Introduction to Time Series and Forecasting, Third Edition, Springer, 2016.
  • RS Tsay, Analysis of Financial Time Series, 2010.
  • Магнус Я. Р. и др., Эконометрика, М., 2014.
7. Main sections of the course
● Characteristics of time series.
● AR, ARMA and ARIMA models.
● Spectral analysis.
● Non-stationary time series.
● Unit roots and structural breaks.
● Multivariate time series.
2nd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ14
1. Purpose of the Course
● introduce students to statistical analysis problems related to several correlated random variables, in particular, study multivariate normal distribution, confidence sets, multivariate hypothesis testing, factor analysis, cluster analysis, etc.
2. Educational Outcomes
a. professional knowledge and expertise
1. represent the relationship of several random variables,
2. test multivariate hypotheses,
3. use the principal components method, factor, cluster analysis methods,
b. practical professional skills
4. work with multivariate distributions,
5. perform multivariate regression,
6. perform cluster, factor and other analyzes with the help of computer software,
c. generic/transferable skills
7. use various information sources.
3. Description
● introduce students to statistical analysis problems related to several correlated random variables, in particular, study multivariate normal distribution, confidence sets, multivariate hypothesis testing, factor analysis, cluster analysis, etc.
4. Teaching and Learning Styles and Methods
1. theoretical lectures,
2. practical work with computers.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Wolfgang Karl Hardle, Léopold Simar, Applied Multivariate Statistical Analysis, 4th Ed ., Springer, 2015.
  • Inge Koch, Analysis of Multivariate and High-Dimensional Data, Cambridge University Press, 2014.
  • Brian Everitt, Torsten Hothorn, An Introduction to Applied Multivariate Analysis with R, Springer, 2011.
  • Daniel Zelterman, Applied Multivariate Statistics with R, Springer, 2015.
7. Main sections of the course
● Multivariate normal distribution
● Copulas
● Credibility sets and hypothesis testing
● Multivariate regression
● Principal components analysis
● Factor analysis
● Cluster analysis
● Discriminant Analysis
● Canonical correlation analysis
2nd semester
Contact hours - 4 hours/week
Lecture-2 hours/week, Practic work-2 hours/week, Individual work-8 hours/week
MANDATORY
0105/Մ13
1. Purpose of the Course
· To teach the basics of machine learning,
· To teach implementing machine learning models in Python,
· To teach modeling large amounts of data and using machine learning models to make predictions based on that data.
2. Educational Outcomes
a. professional knowledge and expertise
1. apply relevant machine learning concepts and methods to formulate and solve practical problems involving large amounts of data;
2. use machine learning models for forecasting and decision making;
3. choose the appropriate model in cases of limited or no information about the dependence between the data;
b. practical professional skills
4. make programs based on machine learning models,
5. determine parameter values of commonly used machine learning models,
6. use Python to analyze large amounts of data, make predictions, and estimate the degree of uncertainty in those predictions.
3. Description
· To teach the basics of machine learning,
· To teach implementing machine learning models in Python,
· To teach modeling large amounts of data and using machine learning models to make predictions based on that data.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam: presentation of a research paper with a maximum value of 4 points (20%).
3. Tests with a maximum value of 4 points (20%).
4. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Bishop, Christopher. Neural Networks for Pattern Recognition. New York, NY. Oxford University Press, 1995.
  • Richard, Peter Hart, and David Stork. Pattern Classification. 2nd ed. New York, NY. Wiley-Interscience, 2000.
  • T., R. Tibshirani, and J.H. Friedman. The Elements of Statistical Learning. Data Mining, Inference and Prediction. New York, NY. Springer, 2001.
  • MacKay, David. Information Theory, Inference, and Learning Algorithms. Cambridge, UK. Cambridge University Press, 2003.
  • Mitchell, Tom. Machine learning. New York, NY. McGraw-Hill, 1997
  • Thomas M., and Joy A. Thomas. Elements of Information Theory. New York, NY. Wiley- Interscience, 1991.
7. Main sections of the course
● Introduction to Machine Learning
● Decision trees​
● Model selection and uncertainty assessment: cross validation, confidence intervals
● Linear regression and regularization methods (Ridge, LASSO)
● Kernels and SVM
● Introduction to Neural Networks
● Mixed models
2nd semester
Contact hours - 2 hours per week
Lecture - 2 hours/week, individual work - 4 hours/week
MANDATORY
0105/Մ08
1. Purpose of the Course
to introduce students to
· the mathematical foundations underlying data processing and communication,
· the methods for measuring information,
· the principles and algorithms of data compression and achievable limits,
· the concept of channel capacity and the principles of constructing error-correcting codes.
2. Educational Outcomes
a. professional knowledge and understanding
1. interpret the mathematical principles, models, and algorithms of data analysis, compression, and transmission,
b. practical professional skills
2. use the methods of information theory to solve applied problems in various fields, such as telecommunications
c. general/transferable skills
3. build codes, evaluate their optimality.
3. Description
to introduce students to
· the mathematical foundations underlying data processing and communication,
· the methods for measuring information,
· the principles and algorithms of data compression and achievable limits,
· the concept of channel capacity and the principles of constructing error-correcting codes.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • T. Cover and J. Thomas, Elements of Information Theory, Wiley, 1991-2006.
  • R. Yeung, Information Theory and Network Coding, 2008 (available online).
  • Shu Lin and D. Costello, Error-Control Coding.
  • W.W. Peterson and E.J. Weldon, Error-correcting codes.
7. Main sections of the course
● Measures of information and their properties.
● Data processing inequality, Fano inequality.
● Data compression, Kraft inequality.
● Huffman and Shannon-Fano-Elias codes.
● Channel: models, coding problem, capacity.
● Hamming codes.
● Information theory and statistics: the method of types.
● Universal source coding.
● Theory of large deviations.
● Error probability in hypothesis testing.
● Data compression subject to a fidelity criterion.
3rd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ15
1. Purpose of the Course
● to acquaint students with classical and modern methods of computer vision, in particular, image processing with neural networks.
2. Educational Outcomes
a. professional knowledge and expertise
1. distinguish different computer vision problems,
2. choose an appropriate solution approach for each problem,
b. practical professional skills
3. use computer vision algorithms to solve various real-world problems.
3. Description
● to acquaint students with classical and modern methods of computer vision, in particular, image processing with neural networks.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical exercises.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Tests with a total maximum value of 6 points (30%).
4. Independent work with a maximum value of 6 points (30%).
6. Basic Bibliography
  • R. Gonzalez, and R. Woods. Digital Image Processing, Prentice Hall, Upper Saddle River, NJ, 2008.
  • Forsyth, David, and Jean Ponce. Computer vision: A modern approach. Prentice Hall, 2011.
7. Main sections of the course
1. Classical methods of Computer Vision,
2. Computer Vision using deep learning methods.
Chair code Name of the elective course Credits
3rd semester
Contact hours - 2 hours per week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
to present models and algorithms necessary for automated processing of text data in the field of natural language processing, as well as for automated extraction of knowledge and automated classification of documents.
2. Educational Outcomes
a. professional knowledge and understanding
1. describe the problems typical in NLP,
2. evaluate NLP-based systems,
b. practical professional skills
3. build high-level processing chains using the basic elements of NLP,
4. choose solutions for typical subproblems of NLP,
5. analyze problems of NLP and break them down into independent components,
c. general/transferable skills
6. break down problems into subproblems,
7. use computer skills effectively.
3. Description
to present models and algorithms necessary for automated processing of text data in the field of natural language processing, as well as for automated extraction of knowledge and automated classification of documents.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • M. Rajman editor, "Speech and Language Engineering", EPFL Press, 2006.
  • Daniel Jurafsky and James H, Martin, "Speech and Language Processing", Prentice Hall, 2008 (2nd edition).
  • Christopher D. Manning and Hinrich Schütze, "Foundations of Statistical Natural Language Processing", MIT Press, 2000.
  • Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press. 2008.
  • Nitin Indurkhya and Fred J. Damerau editors, "Handbook of Natural Language Processing", CRC Press, 2010 (2nd edition).
7. Main sections of the course
● Models and algorithms of automated processing of text data.
● Linguistic engineering.
● Extraction of automated knowledge.
● Automated classification of documents.
● Reflection of text data.
3rd semester
Contact hours - 2 hours per week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ17
1. Purpose of the Course
to provide with knowledge and tools for working with generative models of artificial intelligence.
2. Educational Outcomes
professional knowledge and understanding
1. understand the basics of generative AB models,
b. practical professional skills
2. solve technical problems and create projects,
3. choose appropriate methods and tools,
4. apply generative AB in different fields,
c. general/transferable skills
5. use various sources of information.
3. Description
to provide with knowledge and tools for working with generative models of artificial intelligence.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Oksendal, Bernt. Stochastic differential equations: an introduction with applications. Springer Science & Business Media, 2013.
  • Shreve, Steven E. Stochastic calculus for finance II: Continuous-time models. Vol. 11. New York: springer, 2004.
  • Ho, Jonathan, Ajay Jain, and Pieter Abbeel. "Denoising diffusion probabilistic models." Advances in neural information processing systems 33 (2020): 6840-6851.
  • Song, Jiaming, Chenlin Meng, and Stefano Ermon. "Denoising diffusion implicit models." arXiv preprint arXiv:2010.02502 (2020).
  • Song, Yang, et al. "Score-based generative modeling through stochastic differential equations." arXiv preprint arXiv:2011.13456 (2020).
  • Karras, Tero, et al. "Elucidating the design space of diffusion-based generative models." Advances in neural information processing systems 35 (2022): 26565-26577.
  • Lipman, Yaron, et al. "Flow matching for generative modeling." arXiv preprint arXiv:2210.02747 (2022).
7. Main sections of the course
· KL-Divergence and Variational Auto-Encoders
· Diffusion models: DDPM, DDIM
· Applications: Stable Diffusion
· Score Matching with Langevin Dynamics
· Markov Chain Monte Carlo
· Hamiltonian Monte Carlo and Langevin Dynamics
· Score Matching: Denoising Score Matching (additionally)
· Score-based generative modeling with Stochastic Differential Equations
· Sampling with Probability Flow ODE
· EDM Framework and the Universality Property of Diffusion Models
· Flow Matching and the Connection with Diffusion Models.
3rd semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ17
1. Purpose of the Course
to introduce neural networks, convolutional and recurrent structure of networks, deep unsupervised learning and their applications in voice and image recognition problems.
2. Educational Outcomes
a. professional knowledge and understanding
1. classify neural networks,
2. describe the structure of basic neural networks,
3. distinguish between supervised and unsupervised learning,
b. practical professional skills
4. build programs using deep learning algorithms and train them,
5. solving image recognition problems with the help of convolutional and recurrent networks,
c. general/transferable skills
6. work in a team,
7. effectively apply computer skills.
3. Description
to introduce neural networks, convolutional and recurrent structure of networks, deep unsupervised learning and their applications in voice and image recognition problems.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical exercises,
3. implementation of a group project.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning, 2016.
  • Wiley-Interscience. 2nd Edition. 2001.
  • Russell, S. and Norvig, N. Artificial Intelligence. A Modern Approach. Prentice Hall Series in Artificial Intelligence. 2003.
  • Bishop, CM Neural Networks for Pattern Recognition. Oxford University Press. 1995.
  • Koller, D. and Friedman, N. Probabilistic Graphical Models. MIT Press. 2009.
7. Main sections of the course
● Introduction to Neural Networks
● Learning in neural networks
● Backpropagation​
● Deep learning methods
● Convolutional Neural Networks (CNN)
● Recurrent Neural Networks (RNN)
● Unsupervised deep learning
3rd semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ17
1. Purpose of the Course
to acquaint students with the main problems and methods of biostatistics.
2. Educational Outcomes
professional knowledge and understanding
1. distinguish between methods and models,
b. practical professional skills
2. present the choice of the most appropriate model/method in the given situation,
c. general/transferable skills
3. to use different sources of information.
3. Description
to acquaint students with the main problems and methods of biostatistics.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical works using computer programs.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • B. Rosner, Fundamentals of Biostatistics, Cengage Learning, 7th edition.
  • S. Selvin, A Biostatistics Toolbox for Data Analysis, CUP, 2015.
7. Main sections of the course
- Data collection, presentation and description
- Research planning
- Hypothesis testing for numerical and categorical data
- Correlation analysis
- ANOVA: Analysis of variance
- Factor analysis
3rd semester
Contact hours - 4 hours/week
Lecture - 2 hours/week, pract. work - 2 hours/week, individual work - 8 hours/week
OPTIONAL
0105/Մ16
1. Purpose of the Course
▪ To teach probabilistic machine learning models and the implementation of these models in Python,
▪ To teach modeling large amounts of data and using machine learning models to make predictions based on that data.
2. Educational Outcomes
a. professional knowledge and expertise
1. build an appropriate probabilistic model that characterizes the structure of the data,
2. compare different machine learning models to choose the best one,
b. practical professional skills
3. to program in Python
4. use standard machine learning libraries to make model-based inferences, make predictions based on different models, and estimate the degree of uncertainty of these predictions,
5. apply different methods to compare probabilistic models and choose the best one,
c. generic/transferable skills
6. use various sources of information.
3. Description
▪ To teach probabilistic machine learning models and the implementation of these models in Python,
▪ To teach modeling large amounts of data and using machine learning models to make predictions based on that data.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. Individual and team assignments for students.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Tests with a maximum value of 4 points (20%).
4. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Bishop, Christopher. Neural Networks for Pattern Recognition. New York, NY. Oxford University Press, 1995.
  • Richard, Peter Hart, and David Stork. Pattern Classification. 2nd ed. New York, NY. Wiley- Interscience, 2000.
  • T., R. Tibshirani, and JH Friedman. The Elements of Statistical Learning. Data Mining, Inference and Prediction. New York, NY. Springer, 2001.
  • MacKay, David. Information Theory, Inference, and Learning Algorithms. Cambridge, UK. Cambridge University Press, 2003.
  • Mitchell, Tom. Machine learning. New York, NY. McGraw-Hill, 1997
  • Thomas M., and Joy A. Thomas. Elements of Information Theory. New York, NY. Wiley-Interscience, 1991.
7. Main sections of the course
● Introduction to Bayesian Learning (Generative and Discriminant Models)
● Gaussian processes
● Kalman filter
● Markov models and hidden Markov models
● Graphical models
3rd semester
Contact hours - 4 hours/week
Lecture - 4 hours/week, individual work - 8 hours/week
OPTIONAL
0105/Մ16
1. Purpose of the Course
● introduce students to the theory of random processes and stochastic analysis methods, in particular, to introduce Brownian motion, martingales, Markov processes, the construction of stochastic integral and Ito's formula.
2. Educational Outcomes
a. professional knowledge and expertise
1. describe Brownian motion, martingales, Markov processes, their main properties,
2. describe the construction of stochastic integral and its properties, work with simple stochastic differential equations,
b. practical professional skills
3. use random processes in modeling problems,
4. use the stochastic integral and Ito's formula,
5. perform simulations using computer packages,
c. generic/transferable skills
6. use professional literature, other sources of information,
7. to analyze the existing problems of the field and to propose approaches for solving them.
3. Description
● introduce students to the theory of random processes and stochastic analysis methods, in particular, to introduce Brownian motion, martingales, Markov processes, the construction of stochastic integral and Ito's formula.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical works using computer programs,
3. independent work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. 1st midterm exam with a maximum value of 4 points (20%).
2. 2nd midterm exam with a maximum value of 4 points (20%).
3. Quizzes with a total maximum value of 4 points (20%).
4. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Ovidiu Calin, An Informal Introduction to Stochastic Calculus with Applications, World Scientific, 2015.
  • Paolo Baldi, Stochastic Calculus, An Introduction Through Theory and Exercises, Springer, 2017.
  • Richard Bass, Stochastic Processes, CUP, 2011.
  • Samuel N. Cohen, Robert J. Elliott, Stochastic Calculus and Applications, 2nd Ed ., Springer, 2015.
  • Uwe Hassler, Stochastic Processes and Calculus: An Elementary Introduction with Applications, Springer, 2016.
7. Main sections of the course
● Stochastic processes, general ideas
● Brownian motion
● Martingales
● Markov processes
● Stochastic integration and Ito's calculus
● Stochastic differential equations
3rd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
· To introduce the fundamentals of digital signal processing theory, Fourier transform, structure of filters, discuss the design and implementation of digital filters.
· To present applications of digital signal processing theory using software packages.
2. Educational Outcomes
a. professional knowledge and expertise
1. describe the relationship between digital filters and differential equations,
2. introduce the Fourier transform and its inverse,
3. explain the principles of discrete Fourier transform,
b. practical professional skills
4. apply well-known filters and data analysis algorithms according to their characteristics in practical problems,
5. use the Fourier analysis of stochastic signals,
6. apply software packages for numerical analysis problems,
c. generic/transferable skills
7. make use of professional literature, other sources of information.
3. Description
· To introduce the fundamentals of digital signal processing theory, Fourier transform, structure of filters, discuss the design and implementation of digital filters.
· To present applications of digital signal processing theory using software packages.
4. Teaching and Learning Styles and Methods
1. lectures,
2. team work,
3. individual work.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • V. Oppenheim and RW Schafer, Discrete Time Signal Processing, 2nd Edition, 1998, Prentice Hall .
  • SK Mitra, McGraw-Hill, Digital Signal Processing. A Computer-Based Approach, Third edition, 2006.
  • M. Hays, McGraw-Hill, Schaum's Outline of Digital Signal Processing, 1999.
7. Main sections of the course
● Introduction to Discrete Linear Systems
● Fourier transform
● Discrete Fourier Transform
● Fast Fourier Transform
● Finite and infinite signal response (FIR, IIR) filters
3rd semester
Contact hours - 2 hours per week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
● to submit the main responsibilities of product managers,
● to teach customizing methods of marketing research for products of different types,
● to teach the main frames, concepts and models used in product management,
● to teach financial planning for new products and products portfolio.
2. Educational Outcomes
a. professional knowledge and understanding
1. perform financial planning for new products and products portfolio,
b. practical professional skills
2. apply design thinking in the context of product management,
3. use customer opinion in product management processes,
4. use different methods to generate ideas for new products,
c. general/transferable skills
5. analyze the existing problems, offer solution methods,
6. use various sources of information.
3. Description
● to submit the main responsibilities of product managers,
● to teach customizing methods of marketing research for products of different types,
● to teach the main frames, concepts and models used in product management,
● to teach financial planning for new products and products portfolio.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical work using computer programs,
3. independent work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Bruce T. Barkley, Project Management in New Product Development, McGraw-Hill © 2008 .
  • Cadogan, John, et al. Cross-cultural and cross-national consumer research, Emerald Publishing Limited, 2015. ProQuest Ebook Central, .
  • Charles H. Noble, Serdar S. Durmusoglu and Abbie Griffin Open Innovation: New Product Development Essentials from the PDMA, John Wiley & Sons © 2014. https://library.books24x7.com/toc.aspx?bookid=80723.
7. Main sections of the course
● Product manager as a company in company: responsibilities and qualification.
● Development of ideas and hypotheses for products.
● Product Management Life Cycle Model and Product Home Plan.
● Market Analysis and Customer Opinion for Product Manager.
● Design thinking in product management.
● Finance and predictions for product manager.
3rd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
● To introduce students to the applications of statistics and machine learning, particularly deep learning, in healthcare.
2. Educational Outcomes
a. professional knowledge and expertise
1. formulate real algorithmic problems of medicine/drug production,
b. practical professional skills
2. solve real algorithmic problems of medicine/drug production,
c. generic/transferable skills
3. use the latest methods of machine learning and statistics to solve the above problems.
3. Description
● To introduce students to the applications of statistics and machine learning, particularly deep learning, in healthcare.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical exercises
3. guest lectures by industry experts.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Miguel A. Hernan, James M. Robins (2019). Causal Inference: What if?
  • Trevor Hastie (2008). The Elements of Statistical Learning.
  • Brady Neal (2020). Introduction to Causal Inference.
  • Additional weekly articles and videos.
7. Main sections of the course
Introduction. What is special about medicine?
Clinical care; Features of clinical data
Risk analysis (Risk Stratification)
Survival Analysis
Learning with noisy labels
Disease progression and subtyping analysis
Causal Inference
Dataset Shift
Drug production (invited lecturers)
Machine learning in mammogram analysis
US Laws on Handling Clinical Data (Visiting Lecturers)
3rd semester
Contact hours - 2 hours/week
Lecture-2 hours/week, Individual work-4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
▪ To describe basic methods of random number generation, Monte Carlo and non-parametric statistics;
▪ to give knowledge about generalized linear models, model selection.
2. Educational Outcomes
a. professional knowledge and expertise
1. describe random number generation methods;
2. describe the main methods of non-parametric statistics,
3. compare and select the appropriate statistical model,
b. practical professional skills
4. Perform various calculations with the help of Monte Carlo simulations, Bootstrap methods,
5. estimate density and distribution functions without assuming that they are from any parametric class,
6. to solve specific application problems with the help of the R language,
c. generic/transferable skills
7. analyze existing problems, propose mathematical models, ways of solving them.
3. Description
▪ To describe basic methods of random number generation, Monte Carlo and non-parametric statistics;
▪ to give knowledge about generalized linear models, model selection.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. Completion of individual/team assignments.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Larry Wasserman, All of Nonparametric Statistics, Springer Texts in Statistics, Springer, 2006.
  • James Gentle, Wolfgang Hardle, Yuichi Mori, Handbook of Computational Statistics. Concepts and Methods, 2nd Ed., Springer, 2012.
  • Bradley Efron, Trevor Hastie, Computer Age Statistical Inference. Algorithms, Evidence, and Data Science, CUP, 2016.
  • Geof Givens, Jennifer Hoeting, Computational Statistics, Wiley, 2013.
7. Main sections of the course
● Generating random numbers.
● Monte Carlo methods and MCMC
● The EM algorithm
● Estimation of distribution function, density and statistical functions
● Bootstrap and Jackknife
● Kernels and smoothing
● Nonparametric regression
● GLM
● Model selection
3rd semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work - 4 hours/week
OPTIONAL
0105/Մ18
1. Purpose of the Course
· to teach building reinforcement learning models and implementing these models in Python,
· to introduce dynamic programming and Monte Carlo methods.
2. Educational Outcomes
a. professional knowledge and expertise
1. reformulate problems as Markov decision processes,
2. build an appropriate reinforcement learning model that characterizes the environment, rewards appropriately depending on the action performed,
b. practical professional skills
3. use dynamic programming as an effective solution approach to the problem of industrial management,
4. use reinforcement learning models to program in Python and make inferences based on that models,
c. generic/transferable skills
5. analyze existing problems, propose mathematical models,
6. use various sources of information.
3. Description
· to teach building reinforcement learning models and implementing these models in Python,
· to introduce dynamic programming and Monte Carlo methods.
4. Teaching and Learning Styles and Methods
1. lectures,
2. practical work using computer programs,
3. independent work with computer programs and literature.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Individual work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Reinforcement Learning: An Introduction - Sutton and Barto (2018).
  • Algorithms for Reinforcement Learning - Csaba Szepesvari (2010).
  • Reinforcement Learning: Industrial Applications of Intelligent Agents - Phil Winder (2020).
  • Deep Reinforcement Learning Hands-On - Maxim Lapan (2020).
  • Applied Reinforcement Learning with Python - Taweh Beysolow II (2019).
7. Main sections of the course
· The problems of reinforcement learning
· Multiple armed bandits
· Finite Markov decision processes
· Dynamic programming
· Monte Carlo methods
3rd semester
Contact hours - 2 hours/week
Lecture - 2 hours/week, individual work – 4
OPTIONAL
0105/Մ17
1. Purpose of the Course
· provide deep insight into machine learning graph-based representations;
· equip students with the ability to solve real-world problems using graph algorithms and techniques;
· apply machine learning tools to extract insights from large graphs of social, technological and biological systems.
2. Educational Outcomes
a. professional knowledge and expertise
1. effectively analyze and interpret graph data structures;
b. practical professional skills
2. implement graph neural networks (GNN) for various machine learning problems,
3. evaluate and select appropriate graph-based techniques for specific applications.
3. Description
· provide deep insight into machine learning graph-based representations;
· equip students with the ability to solve real-world problems using graph algorithms and techniques;
· apply machine learning tools to extract insights from large graphs of social, technological and biological systems.
4. Teaching and Learning Styles and Methods
1. theoretical lectures, practical work with computers,
2. completion of individual/team assignments.
5. Evaluation Methods and Criteria
The course is evaluated for a maximum of 20 points.
1. Tests with a maximum value of 6 points (30%).
2. Independent work with a maximum value of 6 points (30%).
3. Final exam with a maximum value of 8 points (40%).
6. Basic Bibliography
  • Graph Representation Learning, William L. Hamilton, 2020.
  • Networks, Crowds, and Markets. Reasoning About a Highly Connected World, David Easley and Jon Kleinberg, 2010.
  • Network Science, Albert-László Barabási, 2016.
7. Main sections of the course
· Introduction to Graph Machine Learning
· Classical methods of machine learning on graphs
· Representations of the vertices
· Link analysis. PageRank:
· Label propagation for vertex classification
· Graph neural networks 1. The GNN model
· Graph Neural Networks 2. Representation space
· Applications of graph neural networks
· The theory of graph neural networks
· Knowledge Graph Representations
· Decision making on the knowledge graph
· Searching for most frequent subgraphs with GNNs
· Community structures in networks
· Deep generative models for graphs
· Additional chapters on GNNs

Other educational modules

Chair code Name of the course Credits
1st semester
Contact hours - 2 hours/week
Seminar-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ19
1. Purpose of the Course
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
2. Educational Outcomes
a. professional knowledge and expertise
1. represent complex structured data in an understandable way,
2. use probability theory in statistics and machine learning,
b. practical professional abilities
3. use the Matplotlib package to plot the data,
4. calculate the probabilities of various events.
3. Description
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
4. Teaching and Learning Styles and Methods
1. Presentations - with Power point materials
2. Practical works - in computer classrooms
5. Evaluation Methods and Criteria
The test is conducted by questionnaires with a maximum value of 20 points. Students who get 10 or more points in the 20-point system from the test will be considered to have passed the test.
6. Main sections of the course
Տիտղոսաթերթ
Ստորագրությունների էջ
Համառոտագիր
Բովանդակություն
Ներածություն
Հիմնական մաս
Եզրակացություններ (և առաջարկություններ)
Օգտագործված գրականության ցանկ
Հավելվածներ
1st semester
Contact hours - 2 hours/week
Seminar-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ19
1. Purpose of the Course
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
2. Educational Outcomes
a. professional knowledge and expertise
1. represent complex structured data in an understandable way,
2. use probability theory in statistics and machine learning,
b. practical professional abilities
3. use the Matplotlib package to plot the data,
4. calculate the probabilities of various events.
3. Description
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
4. Teaching and Learning Styles and Methods
1. Presentations - with Power point materials
2. Practical works - in computer classrooms
5. Evaluation Methods and Criteria
The test is conducted by questionnaires with a maximum value of 20 points. Students who get 10 or more points in the 20-point system from the test will be considered to have passed the test.
6. Main sections of the course
Տիտղոսաթերթ
Ստորագրությունների էջ
Համառոտագիր
Բովանդակություն
Ներածություն
Հիմնական մաս
Եզրակացություններ (և առաջարկություններ)
Օգտագործված գրականության ցանկ
Հավելվածներ
1st semester
Contact hours - 2 hours/week
Seminar-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ19
1. Purpose of the Course
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
2. Educational Outcomes
a. professional knowledge and expertise
1. represent complex structured data in an understandable way,
2. use probability theory in statistics and machine learning,
b. practical professional abilities
3. use the Matplotlib package to plot the data,
4. calculate the probabilities of various events.
3. Description
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
4. Teaching and Learning Styles and Methods
1. Presentations - with Power point materials
2. Practical works - in computer classrooms
5. Evaluation Methods and Criteria
The test is conducted by questionnaires with a maximum value of 20 points. Students who get 10 or more points in the 20-point system from the test will be considered to have passed the test.
6. Main sections of the course
Տիտղոսաթերթ
Ստորագրությունների էջ
Համառոտագիր
Բովանդակություն
Ներածություն
Հիմնական մաս
Եզրակացություններ (և առաջարկություններ)
Օգտագործված գրականության ցանկ
Հավելվածներ
3rd semester
6 weeks
180 hours of independent work
MANDATORY
0105/Մ23
1. Purpose of the Course
● To develop skills and abilities to solve practical problems and to work in the professional enviroment.
2. Educational Outcomes
a. professional knowledge and expertise
1. build algorithms for problems requiring a solution within the framework of practice
2. apply theoretical knowledge to improve the given algorithm
b. practical professional skills
3. process the data to get rid of noise
4. save the received data in a format more convenient for use and application
c. generic/transferable skills
5. collaborate with different people to solve the given problem
3. Description
● To develop skills and abilities to solve practical problems and to work in the professional enviroment.
4. Teaching and Learning Styles and Methods
1. Presentations - with Power point materials,
2. Practical works - in computer classrooms.
5. Evaluation Methods and Criteria
Practice is assessed in the form of a test. Internship is evaluated positively (Pass) if the student participated in the internship, completed the tasks provided by the program, submitted the internship diary within the specified period.
6. Basic Bibliography
  • Krisp
  • PicsArt
  • 0 Web
  • Podcastle
  • VMware
  • WebbFontaine
  • Wolfram Research
  • WorldQuant
  • Intent.ai
7. Main sections of the course
Implementation of professional assignments given by the organization, if necessary with the help of an experienced representative of the organization.
1st semester
Contact hours - 2 hours/week
Seminar-2 hours/week, Individual work-4 hours/week
MANDATORY
0105/Մ19
1. Purpose of the Course
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
2. Educational Outcomes
a. professional knowledge and expertise
1. represent complex structured data in an understandable way,
2. use probability theory in statistics and machine learning,
b. practical professional abilities
3. use the Matplotlib package to plot the data,
4. calculate the probabilities of various events.
3. Description
· introduce the basics of probability theory
· Learn the basics of data visualization
· Introduce students to current trends in machine learning
· Show the range of applications of the obtained knowledge in Armenian companies
· Create an opportunity to learn about the problems of industry representatives and work on their problems.
4. Teaching and Learning Styles and Methods
1. Presentations - with Power point materials
2. Practical works - in computer classrooms
5. Evaluation Methods and Criteria
The test is conducted by questionnaires with a maximum value of 20 points. Students who get 10 or more points in the 20-point system from the test will be considered to have passed the test.
6. Main sections of the course
Տիտղոսաթերթ
Ստորագրությունների էջ
Համառոտագիր
Բովանդակություն
Ներածություն
Հիմնական մաս
Եզրակացություններ (և առաջարկություններ)
Օգտագործված գրականության ցանկ
Հավելվածներ
4th semester
Hours of independent work: 720 hours
Individual work - 720 hours
MANDATORY
0105/Մ24
1. Purpose of the Course
· To familiarize the student with the literature related to the given problem
· To guide the student to solve the problem by collecting and applying algorithms and data needed to solve the given problem
· To teach to formulate the results
· To develop presentation skills
2. Educational Outcomes
b. creative professional abilities
1. Collect and clean data
2. Develop algorithms for solving the given problem
c. generic/transferable skills
3. Do research work
4. Present the results obtained by him
5. Use literature
3. Description
· To familiarize the student with the literature related to the given problem
· To guide the student to solve the problem by collecting and applying algorithms and data needed to solve the given problem
· To teach to formulate the results
· To develop presentation skills
4. Evaluation Methods and Criteria
The thesis is evaluated for a maximum of 20 points.
The following components will be taken into account when evaluating the thesis :
1. Independence
2. Novelty
3. Paper quality
4. Presentation quality
5. Main sections of the course
Title page
Signatures page
Summary
Contents
Introduction
Main part
Conclusions (and recommendations)
Reference list
Applications
Address: Republic of Armenia, Yerevan, 0025, 1 Alex Manoogian (+37460) 710000 info@ysu.am