Certainty in Uncertainty: Exploring Probabilistic Approaches in AI

AI systems are increasingly used in critical decision-making across various sectors. These systems must reason accurately amidst uncertainty, providing reliable support in fields where inaccuracies could have severe consequences.

Workshop topics:

This workshop explores state-of-the-art probabilistic models in AI, highlighting their essential role in making robust decisions under uncertainty. The topics for this workshop are:

• Probabilistic Modelling and Reasoning: Probabilistic machine learning methods that are used in a wide range of different fields with a focus on probabilistic graphical models.
• Causal Inference and Discovery: Methodologies for identifying causal relationships from data. This includes algorithmic approaches, challenges and implications of causal discovery and causal inference.
• Cutting-edge Probabilistic Models: Latest state-of-the-art models such as (Deep) Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Deep Boltzmann Machines, Deep Belief Networks, Bayesian Neural Networks, Deep Markov Models
• Domain-Specific Applications: Submissions that cover the practical applications of probabilistic models in diverse fields such as industry, medicine, and more, showcasing real-world examples.

Important dates:

• 2024-01-31: Electronic submission of workshop papers
• 2024-02-20: Notification of acceptance
• 2024-03-26: AIRoV Symposium

Submission

Information on the format and the submission can can be found here (CALL FOR PAPER).

Chose CIU as workshop track to submit your submission to this workshop.

Organizers

• Anna Christina Glock, Software Competence Center Hagenberg
• David Baumgartner, Norwegian University of Science and Technology & ProbAI
• Michael Mayr, Software Competence Center Hagenberg
• Sabrina Luftensteiner, Software Competence Center Hagenberg

---

More information to come