This session explores advancements in the integration of machine learning and edge intelligence with the theory and practice of neuroscience of movement, under the principles of active inference (AIF).

AIF is a theoretical framework in computational neuroscience, proposing that organisms actively minimize their free energy by continuously updating their internal models of the environment based on sensory input (Parr, Pezzulo, and Friston 2022). AIF is currently used to develop real-time agent-based models (Vries 2023), and to optimize their performance on an Edge infrastructure (Taheri et al. 2023).

In this session, we will first identify the features for a software toolbox for AIF agents. We will then conduct a hands-on session to design AIF agents. Attendees will gain insights into how AIF can be harnessed to solve complex dynamic challenges, the interdisciplinary collaboration necessary for such innovations, and the potential impacts of these advancements.

Program

Introduction and overview (5 minutes)

Keynote presentation: Learning under uncertainty (15 minutes)
Chris Mathys, Aarhus University, Interacting Minds Centre

Interactive workshop: Tools (45 minutes)
on an interactive HPC platform

Wrap-up and panel discussion: Future Directions and Interdisciplinary Collaboration (25 minutes)
Organizers and Chris Mathys

Organizers

• Assoc. Prof. Cumhur Erkut, Aalborg University, cer@create.aau.dk (Main organizer)
• Dr. Carmelo Bellardita, University of Copenhagen, cbellardita@sund.ku.dk
• Assoc. Prof. Melih Kandemir, University of Southern Denmark, kandemir@imada.sdu.dk

Level

Introductory

References

Parr, Thomas, Giovanni Pezzulo, and Karl J Friston. 2022. Active Inference. The MIT Press.

Taheri, Javid, Schahram Dustdar, Albert Zomaya, and Shuiguang Deng. 2023. Edge Intelligence, From Theory to Practice. Springer

Vries, Bert de. 2023. Toward Design of Synthetic Active Inference Agents by Mere Mortals. Communications in Computer and Information Science, 173–85