Keynote

Brain-Artificial Intelligence Interfaces: The Convergence of Artificial and Biological Intelligence

Brain-Computer Interfaces (BCIs) have evolved significantly, transitioning from specialized assistive communication devices for small patient groups to a versatile technology with broad applications. These applications range from post-stroke rehabilitation to systems that monitor cognitive states to enhance human-computer interaction. In this talk, I propose that the next evolutionary step is the transition from Brain-Computer Interfaces to Brain-AI Interfaces (BAIs). Unlike classical BCIs, which primarily decode cognitive states and commands, BAIs integrate AI systems into the cognitive processing pipeline. By interfacing at higher levels of the cortical hierarchy, BAIs have the potential to expand the benefits of neural interfaces to individuals with cognitive impairments. This advancement could revolutionize the way we approach cognitive rehabilitation and assistive technologies. I demonstrate the potential of BAIs through a prototype of a conversational BAI. This prototype enables users to perform complex communication tasks by decoding high-level intentions from brain activity with the low-level details of the task carried out by a large-language model. This capability opens up new possibilities for seamless interaction between humans and AI agents, potentially allowing users to accomplish tasks that surpass human cognitive limitations. By leveraging the strengths of both biological and artificial intelligence, BAIs could pave the way for unprecedented advancements in human-AI collaboration and cognitive augmentation.

Univ.-Prof. Dipl.-Ing. Dr. -Ing. Moritz Grosse-Wentrup is full professor and head of the Research Group Neuroinformatics at the University of Vienna, Austria. He develops machine learning algorithms that provide insights into how large-scale neural activity gives rise to (disorders of) cognition, and applies these algorithms in the domain of cognitive neural engineering, e.g., to build brain-computer interfaces for communication with severely paralyzed patients, design closed-loop neural interfaces for stroke rehabilitation, and develop personalized brain stimulation paradigms. He has received numerous awards for his work, including the 2011 Annual Brain-Computer Interface Research Award, the 2014 Teaching Award of the Graduate School of Neural Information Processing at the University of Tübingen, and the 2016 IEEE Brain Initiative Best Paper Award.