The free energy principle from neuroscience provides an efficient data-driven framework called the Dynamic Expectation Maximization (DEM), to learn the generative model in the environment. DEM’s growing potential to be the brain-inspired learning algorithm for robots demands a mathematically rigorous analysis using the standard control system tools. Therefore, this paper derives the mathematical proof of convergence for its parameter estimator for linear state space systems, subjected to colored noise. We show that the free energy based parameter learning converges to a stable solution for linear systems. The paper concludes by providing a proof of concept through simulation for a wide range of spring damper systems.
|Title of host publication
|Machine Learning and Principles and Practice of Knowledge Discovery in Databases
|Subtitle of host publication
|Proceedings of the International Workshops of ECML PKDD 2021
|Michael Kamp, Michael Kamp, Irena Koprinska, et. al.
|Published - 2022
|21st European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2021 - Virtual, Online
Duration: 13 Sept 2021 → 17 Sept 2021
|Communications in Computer and Information Science
|21st European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2021
|13/09/21 → 17/09/21
Bibliographical noteGreen Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
- Dynamic expectation maximization
- Free energy principle
- Linear state space systems
- Parameter estimation