Бакалавриат
2025/2026
Научно-исследовательский семинар "Современные инструменты компьютерных вычислений"
Статус:
Курс обязательный (Прикладная математика)
Кто читает:
Департамент прикладной математики
Когда читается:
2-й курс, 1-4 модуль
Охват аудитории:
для всех кампусов НИУ ВШЭ
Язык:
английский
Кредиты:
4
Контактные часы:
40
Course Syllabus
Abstract
The workshop is aimed at getting skills to work with the scientific stack of the Python language: Numpy, Matplotlib, Scipy, Pandas. As a result of mastering the workshop, the student will learn how to interact with the Jupiter Notebook interactive environment, apply numerical methods to solve problems (Scipy), analyse the results obtained (Pandas), build graphs (Matplotlib).The course introduces the theory and practice of machine learning algorithms. Students will learn data preprocessing methods, dimensionality reduction techniques, modeling techniques using machine learning algorithms, and parameter tuning.The algorithms studied include linear regression with regularization (ridge regression, elastic net, lasso), multivariate adaptive regression splines, support vector machines, k-nearest neighbors, classification and regression trees, random forest.Students explore the capabilities of the PyTorch library for solving problems of relevant machine learning task classes.
Learning Objectives
- Acquiring knowledge and skills in programming in Python and using widely applicable modules of the scientific stack (Numpy, Scipy, Matplotlib, Pandas).
- Acquiring skills in using Python functions from various Python packages to apply various types of models, such as linear and nonlinear regression models, linear and nonlinear classification models, regression trees and rule-based models.
- Acquiring skills in using Python functions from various Python packages for preliminary processing of input data, i.e. calculating statistics, estimating asymmetry, applying an appropriate transformation, performing principal component analysis, searching for correlations between predictors, generating dummy variables.
- Acquiring skills in working with the PyTorch library for relevant classes of machine learning problems.
Expected Learning Outcomes
- Familiar with the basic concepts and directions of machine learning
- Has skills of data preprocessesing using Pandas.
Course Contents
- Introduction to machine learning
- Data preprocessing
- Linear regression models
- Support vector machine. K-nearest neighbors method
- Linear classification models
- Decision trees
- Advanced ML tasks using the PyTorch library
Assessment Elements
- Домашнее заданиеДомашнее задание
- Домашнее задание
- Домашнее задание
- Домашнее задание
- Защита проектной работы
Interim Assessment
- 2025/2026 4th module0.1 * Домашнее задание + 0.1 * Домашнее задание + 0.2 * Домашнее задание + 0.2 * Домашнее задание + 0.4 * Защита проектной работы
Bibliography
Recommended Core Bibliography
- Foundations of machine learning, Mohri, M., 2012
- Machine learning fundamentals : a concise introduction, Jiang, H., 2021
- Nelli, F. (2018). Python Data Analytics : With Pandas, NumPy, and Matplotlib (Vol. Second edition). New York, NY: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1905344
- Pandas for everyone : Python data analysis, Chen, D. Y., 2023