Predictive Processing: Exploring Multivalent Variables
dc.contributor.advisor | Kwisthout, J.H.P. | |
dc.contributor.author | Verheijden, D.M.J. | |
dc.date.issued | 2017-07-04 | |
dc.description.abstract | Our 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.uri | http://theses.ubn.ru.nl/handle/123456789/4380 | |
dc.language.iso | en | en_US |
dc.thesis.faculty | Faculteit der Sociale Wetenschappen | en_US |
dc.thesis.specialisation | Bachelor Artificial Intelligence | en_US |
dc.thesis.studyprogramme | Artificial Intelligence | en_US |
dc.thesis.type | Bachelor | en_US |
dc.title | Predictive Processing: Exploring Multivalent Variables | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Verheijden, D._BSc_Thesis_2017.pdf
- Size:
- 2.74 MB
- Format:
- Adobe Portable Document Format
- Description:
- Thesis text