Thesis supervisor: László Gulyás
co-supervisor: Péter Érdi
Location of studies (in Hungarian): ELTE, Faculty of Informatics Abbreviation of location of studies: ELTE
Description of the research topic:
With the ongoing explosion in the capabilities of large-scale artificial intelligence (AI) models, generative AI has gained huge popularity. Current foundation models are seemingly able to interpret human text and generate responses interactively. AI-based tools are available for common engineering tasks, like code and test generation, information retrieval from large document databases.
Much of the engineering work is centered around human text. System and software requirements are still formulated in human language, processes and procedures are described in text, possibly with some diagrams. The documentation effort for complex, safety-critical product development far outweighs the effort of pure coding. Harnessing the power of AI-based tools to help engineers with text-based engineering work has large potential benefits. It is also very important to understand the limitations of such systems and develop methods to mitigate their risks. Large engineering organizations have vast amounts of product development data accumulated over the years. From customer requirements through system and software design down to the implementation, as well as test specifications and results, including change management and other artifacts. This data is an excellent basis for the development of AI systems supporting work on engineering design.
The focus of this research is to investigate new approaches to integrate AI and machine learning (ML) into the mature development processes typically used in large engineering organizations. Extending the current foundation models with semantic processing is an active field of research. At the same time, model-based system engineering methods and tools are increasingly capable, yet their adoption in large projects requires considerable effort. The goal is the development of a new methodology for the effective integration of AI technology into complex development processes.
Required language skills: angol Recommended language skills (in Hungarian): B1 Further requirements: MSc in one of the following fields: informatics, software engineering, computer science or related areas.
Fluent in English.
Number of students who can be accepted: 2
Deadline for application: 2024-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
