Bachelor
2024/2025
Research Seminar "Data Analysis and Artificial Intelligence"
Type:
Compulsory course (Applied Mathematics and Information Science)
Area of studies:
Applied Mathematics and Information Science
Delivered by:
School of Data Analysis and Artificial Intelligence
Where:
Faculty of Computer Science
When:
3 year, 1-4 module
Mode of studies:
offline
Open to:
students of one campus
Language:
English
ECTS credits:
4
Course Syllabus
Abstract
The discipline goal is to develop students' professional skills required for independent analytical work in applied fields of the computer science. The course consists of two parts: Bioelectrical digital signal processing and Introduction to the Semantic Web Technologies. The former aims to improve skills of students in developing their research projects related with digital signal processing. The course program includes two main parts. The first part is an introduction in digital signal processing (DSP) theory. The second part covers practical issues of DSP theory application to the problem of brain-computer interfaces development – one of the major fields in modern neuroscience. The latter is a gentle introduction to the theory and practice of the Semantic Web, an extension of the current Web that provides an easier way to find, share, reuse and combine information. It is based on machine-readable information and builds on XML technology's capability to define customized tagging schemes, RDF's (Resource Description Framework) flexible approach to representing data, the OWL (Web Ontology Language) schema language and SPARQL query language. The Semantic Web provides common formats for the interchange of data (where on the Web there is only an interchange of documents). It also provides a common language for recording how data relates to real world objects, allowing a person or a machine to start off in one database, and then move through an unending set of databases which are connected not by wires but by being about the same thing. Important applications of the Semantic Web technologies include Healthcare (SNOMED CT), Supply Chain Management (Biogen Idec), Media Management (BBC), Data Integration in the Oil & Gas industry (Chevron, Statoil), Web Search and E-commerce.
Learning Objectives
- Students develop a comprehensive picture of the current state of various areas where deep learning models are applied, their development trajectory, and the potential successes of new methods. In this way, students can delve into a subject area in more detail, find their personal interests in a particular area, and learn to work through complex material in a limited time frame.
Expected Learning Outcomes
- Presentation of reports on scientific topics
- Immersion in scientific material at the intersection of higher mathematics, deep learning and, in particular cases, narrow subject areas (e.g. Bioinformatics)
- Search for scientific materials, research of sources
- Writing code based on the results of developments by authors of scientific publications, applying it to your own tasks
Course Contents
- Real Top-dog: Transformer
- Deep learning applications for Computer Vision
- AI-strategies for 2D Image Generation
- Understanding 3D Model Generation
- Our Future: Large Language models
- Audio Generation: from text to sounds
- Explore the neural networks: xAI
- Image Generation via LM: intersecting two areas
- Optimising Neural Networks
- Self-Supervised Learning: why do we need it?
- Contrastive learning
- Reinforcement learning: game of policy & strategy
- NeRF family: new stage of 3D rendering
- Object Tracking: everything & everywhere
- Graph neural networks: new form of convolution
- BioInformatics: when AI meets DNA
- Audio: another attempt
Interim Assessment
- 2024/2025 4th module0.5 * Оценка (среднее за 2 доклада) + 0.2 * Оценка (среднее за две рецензии) + 0.3 * Оценка (среднее за 2 теста)
