BIASlab
BIASlab
  • TU/e logo
  • SPS
  • BIASlab
  • Research
    Projects Publications Colloquium
  • Software
    RxInfer.jl ReactiveMP.jl GraphPPL.jl Rocket.jl ForneyLab.jl
  • Teaching
    5ARA0 Software Engineering for Artificial Intelligence 5SSD0 Bayesian Machine Learning
  • Team
  • Contact
  • Light Dark Automatic
Magnus Koudahl

Magnus Koudahl

Former PhD student

Former BIASlab Member

Magnus defended his PhD thesis in 2024. He now works at VERSES. His research centered on fusing Active Inference and Bayesian Machine learning to create novel solutions for Reinforcement Learning problems.

Interests
  • Computational Neuroscience
  • Bayesian Machine Learning
  • Reinforcement Learning

Latest

  • Realising Synthetic Active Inference Agents, Part II: Variational Message Updates
  • Realising Synthetic Active Inference Agents, Part I: Epistemic Objectives and Graphical Specification Language
  • Gaussian Process-based Amortization of Variational Message Passing Update Rules
  • Active Inference and Epistemic Value in Graphical Models
  • Variational message passing for online polynomial NARMAX identification
  • AIDA: An active inference-Based design agent for audio processing algorithms
  • On Epistemics in Expected Free Energy for Linear Gaussian State Space Models
  • Learning Where to Park
  • A Worked Example of Fokker-Planck based Active Inference
  • BATMAN: Bayesian target modelling for active inference

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.

Cite
Copy Download