|
Lecturer(s)
|
|
|
|
Course content
|
Teams choose or are given one of the appropriate topics, e.g.: - Intelligent search in archival documents - Automatic classification of archival materials - OCR and processing of historical documents - Extracting information from text - AI chatbot over archival database - Visualization of historical data - Linking archival sources (knowledge graph) - Analysis of manuscripts or historical images - Semantic search in cultural archives
|
|
Learning activities and teaching methods
|
Dialogic (discussion, interview, brainstorming), Laboratory, Project-based learning, Practical training
- Preparation for classes
- 36 hours per semester
- Semestral paper
- 44 hours per semester
- Class attendance
- 36 hours per semester
- Field trip
- 4 hours per semester
|
|
Learning outcomes
|
The Hackathon - Smart Archives: Unlocking Knowledge with AI course is an intensive project activity focused on the design and implementation of prototypes of tools for working with archival data using artificial intelligence methods. During the 24-hour hackathon, students work in teams to solve real-world problems associated with the digitization, analysis, and accessibility of archival documents. The goal is to use modern technologies (e.g., machine learning, natural language processing, computer vision, or generative AI) to create a prototype of a tool that will enable more efficient searching, classification, interpretation, or visualization of historical and archival data. The hackathon simulates an environment for the rapid development of innovative solutions, supporting creativity, interdisciplinary collaboration, and the practical application of knowledge in computer science, data science, and digital humanities.
After completing the course, the student should be able to understand the basic problems of digital archives and working with historical data, be able to design a prototype of a software solution using AI, master the principles of rapid prototyping, gain experience with teamwork under time pressure, and be able to present and defend a technological solution.
|
|
Prerequisites
|
There are no prerequisites for the course. Basic knowledge of programming, working with data, and knowledge of AI (machine learning) are an advantage.
|
|
Assessment methods and criteria
|
Student performance assessment, Analysis of student's work activities (technical works), Seminar work
Course requirements: Each team submits: - project source code - short documentation (2-4 pages) - project presentation - functional prototype or demo
|
|
Recommended literature
|
-
MDN Web Docs.
-
ALBADA, Michael. Building Applications with AI Agents: Designing and Implementing Multi-Agent Systems. O'Reilly Media, 2025. ISBN 978-1-098-17650-1.
-
BOURNE, Keith. Unlocking data with generative AI and RAG: enhance generative AI systems by integrating internal data with large language models using RAG. Birmingham: Packt Publishing, 2024. ISBN 978-1-83588-790-5.
-
BOURNE, Keith. Unlocking Data with Generative AI and RAG: Learn AI agent fundamentals with RAG-powered memory, graph-based RAG, and intelligent recall. O'Reilly Media, 2025. ISBN 978-1-80638-165-4.
-
Collins, M. J. Pro HTML5 with CSS, JavaScript, and Multimedia: Complete Website Development and Best Practices. Chesterfield, Virginia (USA): Apress, 2017. ISBN 978-1-4842-2462-5.
-
RUSSELL, Stuart J. a NORVIG, Peter. Artificial intelligence: a modern approach. Hoboken: Pearson, 2021. ISBN 978-0-13-461099-3.
|