Natural Artificial Intelligence
Automating the development of novel signal processing and control systems through neuro-inspired free-energy minimizing agents
Find out moreNatural Artificial Intelligence
Automating the development of novel signal processing and control systems through neuro-inspired free-energy minimizing agents
Find out moreThe goal of this project was to build an assistive tool that could help Football coaches to simulate the actions of an “optimally behaving” defensive team. We developed a cost function that optimizes both Pitch Control and Pass Interceptions for the defensive team.
In order to assess the feasibility of active inference as a framework for synthetic agents in a real-world setting, we developed a ground-based robot that needs to learn to navigate to an undisclosed parking location. The robot can only learn where to park through situated interactions with a human observer who is aware of the target location.
ForneyLab is a novel Julia package that allows the user to specify a probabilistic model as an FFG and pose inference problems on this FFG. ForneyLab is especially potent when applied to time-series data, where it attains comparable performance to Stan and Edward in significantly less computation time.
Multiple variational Kalman-GRU for ship trajectory prediction with uncertainty
GraphPPL.jl: A Probabilistic Programming Language for Graphical Models
Improved Depth Estimation of Bayesian Neural Networks
Coupled autoregressive active inference agents for control of multi-joint dynamical systems
Our Mission: Bayesian Intelligent Agents
The primary mission of the BIASlab team is to develop in-situ trainable Bayesian Intelligent Agents for applications to wearable technology.
Our Approach to Solving Difficult Design Problems
How do you solve a problem that is only vaguely described? We describe here an engineering approach that guides our research on solving vaguely defined problems such as hearing impairment.
Bert de Vries
Professor, TU Eindhoven
Thijs van de Laar
Assistant professor, TU Eindhoven
Wouter Kouw
Assistant professor, TU Eindhoven
Dmitry V. Bagaev
Postdoctoral fellow, TU Eindhoven
Bart van Erp
PhD candidate - Teaching Assistant, TU Eindhoven
Hoang Minh Huu Nguyen
PhD candidate, TU Eindhoven
Tim Nisslbeck
PhD candidate, TU Eindhoven
Mykola Lukashchuk
PhD candidate, TU Eindhoven
Sepideh Adamiat
PhD candidate, TU Eindhoven
Wouter Nuijten
PhD candidate, TU Eindhoven
Raaja Ganapathy Subramanian
PhD candidate, TU Eindhoven
Marco Hidalgo Araya
PhD candidate, TU Eindhoven
Raphaël Trésor
PhD candidate, TU Eindhoven
Fons van der Plas
Educational Developer, TU Eindhoven
MSc project: Probabilistic programming for printhead diagnostics.
System diagnostics: develop a maintenance support tool for printhead malfunction.
MSc project: Acoustic source separation for hearables.
Signal processing: develop a probabilistic model for acoustic source separation.
MSc project: Active inference for robot locomotion.
Control systems: develop a controller to make a four-legged robot learn to walk.
We gratefully acknowledge financial support from our sponsors:
