SluitenHelpPrint
Switch to English
Cursus: INFOMLSAI
INFOMLSAI
Logics for safe AI
Cursus informatie
CursuscodeINFOMLSAI
Studiepunten (EC)7,5
Cursusdoelen

Upon successful completion of this course, a student:
 
- Knows the logical and computational techniques for specifying, verifying and synthesising the behaviour of AI agents and multi-agent systems, and the limitations of these techniques
 
- Is able to read and assess the research literature in this field
 
- Is able to use appropriate underlying logical formalisms as a framework for specifying, verifying and synthesising the behaviour of AI agents and multi-agent systems, and has a good understanding of the computational aspects of these formalisms
 
- Is able to use appropriate tools implementing these techniques to specify, verify and synthesise the behaviour of AI agents and multi-agent systems
 
- Acquires a mastery of technical artificial intelligence at an advanced academic level 


Assessment

One final exam, pass grade 6/10. 

Inhoud
This course is about ensuring the safety and reliability of autonomous AI agents and multi-agent systems.
In order to guarantee that the behavior of a system achieves its objectives, we use formal proofs rather than empirical studies, and either formally verify that the system behaves in accordance with the specified objectives, or automatically synthesise provably correct behaviours from specifications of the system objectives.
The formal techniques for doing this include epistemic and temporal logics and their combinations, and constitute the main technical content of the course. The emphasis is on mastering these techniques, their computational aspects, and the use of tools implementing them to verify and synthesise AI agents and multi-agent systems.
The course also prepares students for undertaking research on formal aspects of artificial intelligence, and provides the foundation for undertaking Masters projects on developing safe and reliable AI systems. Lab sessions will introduce students to relevant specification and modelling techniques and the use of tools such as MCMAS and SynKit for the verification and synthesis of AI agents and multi-agent systems. 

For further details see the Blackboard information given on
https://uu.blackboard.com/webapps/blackboard/content/listContent.jsp?course_id=_128773_1&content_id=_3482207_1

Course format
Two lectures a week and a lab/practical session for mastering techniques and tools for the specification, verification and synthesis of AI agents and multi-agent systems.


 
SluitenHelpPrint
Switch to English