Natural Artificial Intelligence

Automating the development of novel signal processing and control systems through neuro-inspired free-energy minimizing agents

Find out more

Natural Artificial Intelligence

Automating the development of novel signal processing and control systems through neuro-inspired free-energy minimizing agents

Find out more

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.

Read more

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.

Read more

We develop a fully probabilistic approach to pure-tone audiometry. By assuming a Gaussian process based response model for test tones, the hearing threshold estimation problem becomes one of Bayesian inference. This allows the use of information-theoretic criteria to select optimal test tones.

Read more

More Projects

More Publications

The primary mission of the BIASlab team is to develop in-situ trainable Bayesian Intelligent Agents for applications to wearable technology.

Read more

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.

Read more

Bert de Vries

Professor, TU Eindhoven

Thijs van de Laar

Postdoctoral fellow, TU Eindhoven

Wouter Kouw

Postdoctoral fellow, TU Eindhoven

Dmitry V. Bagaev

PhD candidate, TU Eindhoven

Patrick Wijnings

PhD candidate, TU Eindhoven

Magnus Tønder Koudahl

PhD Candidate, TU Eindhoven

Albert Podusenko

PhD candidate, TU Eindhoven

Martin Roa Villescas

PhD candidate, TU Eindhoven

Ismail Senoz

PhD candidate, TU Eindhoven

Ivan Bocharov

PhD candidate, TU Eindhoven

Semih Akbayrak

PhD candidate, TU Eindhoven

Marco Cox

PhD candidate, TU Eindhoven

Joris Kraak

Senior Software Engineer, GN Hearing

Full team

In this project you will study how two active inference agents can cooperate to solve a task.

Read more

In this project you will simulate a Bayesian machine learning algorithm on a neuromorphic chip.

Read more

In this project you will develop an agent to infer the dynamical parameters of an electro-mechanical positioning system.

Read more

All open projects

We gratefully acknowledge financial support from our sponsors:

NWO
GN Resound