Dear all,

this is a reminder for Joost-Pieter Katoen's talk with the title "Facing Uncertainty in AI: From Verification to Synthesis" taking place today at 12:30 in the B-IT room 5053.2. Please find the details below

--- Abstract ---

Uncertainties occur in different forms: data may be noisy, mechanisms 

may be inherently randomised, the visibility (of e.g. a robot) may not 

be optimal, and the environment in which a system needs to operate may 

behave in an unknown manner. The central question that we will address 

is "Can we guarantee that AI systems are safe and dependable in the 

presence of such uncertainty?'' We advocate using model-based, formal 

verification and synthesis with a particular focus on automation. We 

will present techniques to verify uncertainty aspects modeled as 

randomness and to use formal synthesis to complete partial designs. 

Several example AI systems will illustrate the capabilities of these approaches.

----------------

Part of the programme of the research training group UnRAVeL is a series of lectures on the topics of UnRAVeL’s research thrusts algorithms and complexity, verification, logic and languages, and their application scenarios. Each lecture is given by one of the researchers involved in UnRAVeL.

This years topic is "UnRAVeL - New Ideas!". In these lectures, UnRAVeL professors will discuss current research as well as highlight open problems and offer a perspective on potential future directions.

All interested doctoral researchers and master students are invited to attend the UnRAVeL lecture series 2024 and engage in discussions with researchers and doctoral students.

We are looking forward to seeing you at the lectures.

Kind regards,
Jan-Christoph for the organisation committee