Selected Topics in Data Science

2022/2023

Учебный год

ENG

Обучение ведется на английском языке

3

Кредиты

Кто читает:

Департамент политологии и международных отношений

Статус:

Курс по выбору

Когда читается:

1-й курс, 4 модуль

Преподаватель

Серебренников Дмитрий Евгеньевич

Course Syllabus

Abstract

Somebody could argue that machine learning is the most transformative technology to develop in recent decades. We provide an overview of the main ML approaches in this course in the context of social sciences and the attention that researchers have given to these methods. Basic probability and statistics, high school linear algebra, and basic calculus are requirements for this course. R, an open source statistical language, will be used throughout the course. Tidyverse knowledge is necessary, while data.table skill is desirable.

Learning Objectives

• The goal of this course is to acquaint students with data science methods and terminology, and to teach them how to implement these methods using R programming language.

Expected Learning Outcomes

• • Knows key machine learning concepts
• Extracts insights from analysis of the models
• • Handles different kinds of data and ML methods
• • Realizes how to implement basic ML models in R
• • Understands how social scientists use ML tools

Course Contents

• Topic 1: Intro to Data Science.
• Topic 2: Unsupervised Learning: Dimension Reduction.
• Topic 3: Introduction to Supervised Learning: Regression and Regularization.
• Topic 4: Ensemble methods.
• Topic 5: Introduction to Deep Learning.
• Topic 6: Interpretable Machine Learning (IML) / Explainable AI (XAI).
• Topic 7: Data Harvasting.

Assessment Elements

• Participation
• Five Homeworks
  50%. Students will have 5 homeworks during the course. You will have to write them using Rmarkdown and send a html file via email to course instructor. Each homework will grade from 1 to 10 and bring an appropriate amount of percentage to the final grade.
• Quizzes
  During the course you will take 6 quizzes. They will be at the first part of the class. Each of them will consist of 5 questions and right answer on a question bring 1% to overall score. Therefore one quiz could bring you 5%.
• Final presentation

Interim Assessment

• 2022/2023 4th module
  0.5 * Five Homeworks + 0.1 * Participation + 0.1 * Final presentation + 0.3 * Quizzes

Bibliography

Recommended Core Bibliography

• Gareth James, Daniela Witten, Trevor Hastie, & Robert Tibshirani. (2013). An Introduction to Statistical Learning : With Applications in R. Springer.

Recommended Additional Bibliography

• Murphy, K. P. (2012). Machine Learning : A Probabilistic Perspective. Cambridge, Mass: The MIT Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=480968