Goal conditional episodic replay

Simple item page
dc.contributor.advisorGerven, Marcel van
dc.contributor.advisorAmbrogioni, Luca
dc.contributor.authorPanagiotou, Filippos
dc.date.issued2018-10-22
dc.description.abstractThe human brain employs sophisticated schemes to store and reuse accumulated information. Episodic memory is one such strategy: temporally dependent event sequences are encoded and stored, and then replayed for beneficial effects for the collected information. In this research an algorithm is employed where episodes are created by a series of stacked Recurrent Neural Networks (RNNs). Information at different points of the processing is stored as the hidden states of the corresponding RNN. Another RNN is subsequently used to generate episodes given partial information of the encoded episodes, and a pre-set intended answer. The results show that the use of novel episodic replay allows the network to increase the speed of convergence in some of the 20 QA bAbI tasks.en_US
dc.embargo.lift10000-01-01
dc.embargo.typePermanent embargoen_US
dc.identifier.urihttps://theses.ubn.ru.nl/handle/123456789/10735
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeMasteren_US
dc.titleGoal conditional episodic replayen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
S4645227_Panagiotou F 2018.pdf
Size:
2.16 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculteit der Sociale Wetenschappen