Predictive Processing: Exploring Multivalent Variables

Simple item page
dc.contributor.advisorKwisthout, J.H.P.
dc.contributor.authorVerheijden, D.M.J.
dc.date.issued2017-07-04
dc.description.abstractOur research extends the causal Bayesian network implementation of the Predictive Processing Theory to account for multivalent variables. We also propose a framework for solving the exploration-exploitation trade-o in the Bayesian Predictive Processing implementation. Here we use a Q-Learning approach with Dirichlet distributions as hyperpriors and the free-energy principle as a base for learning. The latter links the proposed methods to neural mechanisms in the brain which have been linked to the exploration/exploitation trade-o . We tested our methods via behavioural studies where a robot had to learn an environment from scratch to navigate to a light source.en_US
dc.identifier.urihttp://theses.ubn.ru.nl/handle/123456789/4380
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationBachelor Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeBacheloren_US
dc.titlePredictive Processing: Exploring Multivalent Variablesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Verheijden, D._BSc_Thesis_2017.pdf
Size:
2.74 MB
Format:
Adobe Portable Document Format
Description:
Thesis text
Download
Collections
Faculteit der Sociale Wetenschappen