07-12, 09:00–10:00 (Europe/Amsterdam), REPL (2, main stage)
Large language model-based chatbots such as chatGPT are very impressive, but you cannot ask them to go out and learn how to ride a bike. Learning how to ride a bike is about an agent that learns a skill through efficient, real-time interactions with a dynamic environment. In this presentation, I will discuss the underlying technology that enables brains to learn new skills and acquire knowledge solely through unsupervised environmental interactions.
Large language model-based chatbots such as chatGPT are very impressive, but you cannot ask them to go out and learn how to ride a bike. Learning how to ride a bike is about an agent that learns a skill through efficient, real-time interactions with a dynamic environment. In this presentation, I will discuss the underlying technology that enables brains to learn new skills and acquire knowledge solely through unsupervised environmental interactions. How much do we understand about what brains compute? And is this knowledge transferable to AI engineering systems? I will discuss Karl Friston’s Free Energy Principle, which is the theory on what, why and how brains compute. I will also discuss the efforts of our research lab (http://biaslab.org) at TU Eindhoven to develop a Julia ecosystem of packages to support transfer of these ideas to working AI engineering tools.
Bert de Vries received MSc (1986) and PhD (1991) degrees in Electrical Engineering from Eindhoven University of Technology (TU/e) and the University of Florida, respectively. From 1992 to 1999, he worked as a research scientist at Sarnoff Research Center in Princeton (NJ, USA). Since 1999, he has been employed in the hearing aid industry, both in engineering and managerial positions. De Vries was appointed professor in the Signal Processing Systems Group at TU/e in 2012. His research focuses on the development of intelligent autonomous agents that learn from in-situ interactions with their environment. We aim to use these agents to automate the development of novel signal processing and control algorithms, see biaslab.org. Our research draws inspiration from diverse fields including computational neuroscience, Bayesian machine learning, and signal processing systems. A current major application area concerns the personalization of medical signal processing systems such as hearing aid algorithms.