Департамент анализа данных и искусственного интеллекта

АБB
АБB
АБB

Обычная версия сайта

Департамент анализа данных и искусственного интеллекта был создан в 2014 году на базе кафедры анализа данных и искусственного интеллекта. В его состав входят исследователи с мировым именем, активно участвующие в международных исследовательских проектах.

Публикации

Книга

17th International Conference, SCSM 2025, Held as Part of the 27th HCI International Conference, HCII 2025, Gothenburg, Sweden, June 22–27, 2025, Proceedings, Part II. Social Computing and Social Media. LNCS, volume 15787

Fedyanin D.

Vol. 2. Switzerland: Springer, 2025.

Статья

Relative Chaoticity of Natural Languages

Yerbolova A. S., Tomashchuk K., Kogan A. et al.

Complexity. 2026. Vol. 2026. No. 1.

Глава в книге

KoWit-24: A Richly Annotated Dataset of Wordplay in News Headlines

Alexander Baranov, Anna Palatkina, Makovka Y. et al.

In bk.: Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing. Shumen: INCOMA Ltd, 2025. P. 125-132.

Препринт

Hessian-based lightweight neural network for brain vessel segmentation on a minimal training dataset

Меньшиков И. А., Бернадотт А. К., Elvimov N. S.

Statistical mechanics. arXie. arXive, 2025

Все публикации

Кто читает:: Департамент анализа данных и искусственного интеллекта

Статус:: Маго-лего

Когда читается:: 3, 4 модуль

Преподаватели

Коган Александра Сергеевна

Поздняков Виталий Витальевич

Full Syllabus Ask Question

Abstract

The course “Network Science” introduces students to new and actively evolving interdisciplinary field of network science. Started as a study of social networks by sociologists, it attracted attention of physicists, computer scientists, economists, computational biologists, linguists and others and become a truly interdisciplinary field of study. In spite of the variety of processes that form networks, and objects and relationships that serves as nodes and edges in these networks, all networks poses common statistical and structural properties. The interplay between order and disorder creates complex network structures that are the focus of the study. In the course we will consider methods of statistical and structural analysis of the networks, models of network formation and evolution and processes developing on network. Special attention will be given to the hands-on practical analysis and visualization of the real world networks using available software tools and modern programming languages and libraries.

Learning Objectives

To familiarize students with a new rapidly evolving filed of network science, and provide practical knowledge experience in analysis of real world network data.

Expected Learning Outcomes

Know basic notions and terminology used in network science
Understand fundamental principles of network structure and evolution.
Can develop mathematical models of network processes.
Can analyze real world network data.

Course Contents

Introdiction to network science
Scale-free networks
Random networks
Network models
Node centrality and ranking on networks
Structural properties of networks
Community detection in networks
Epidemics on networks
Cascades and influence maximization
Node classification
Link prediction
Graph embedding
Graph neural networks
GNNs in practice
Theoretical foundations of GNNs
Knowledge graphs

Assessment Elements

Домашнее задание
Тест
Индивидуальный проект
Соревнование
Экзамен

Interim Assessment

2025/2026 4th module
0.33 * Тест + 0.25 * Экзамен + 0.17 * Домашнее задание + 0.17 * Соревнование + 0.08 * Индивидуальный проект

Bibliography

Recommended Core Bibliography

A first course in machine learning, Rogers, S., 2012

Recommended Additional Bibliography

Network science, Barabasi, A.-L., 2019

Authors

Антропова Лариса Ивановна

Network Science