Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/62219
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Wenwenen
dc.date.accessioned2015-02-27T04:06:36Zen
dc.date.available2015-02-27T04:06:36Zen
dc.date.copyright2015en
dc.date.issued2015en
dc.identifier.citationWang, W. (2015). Neural modeling of multiple memory systems and learning. Doctoral thesis, Nanyang Technological University, Singapore.en
dc.identifier.urihttps://hdl.handle.net/10356/62219en
dc.description.abstractThis thesis presents a biologically inspired multi-memory system for modeling the structures and connections between the procedural and declarative memories. Using multi-channel self-organizing neural networks as building blocks, the proposed multi-memory system includes a procedural memory model that learns decision through reinforcement learning, an episodic memory model that encodes an individual's experience in the form of events and their spatio-temporal relations, and a semantic memory that captures factual knowledge. We have further proposed two major interaction process between the three memories. We further investigated the overall performance of the memory system on a first person shooting game and a Starcraft Broodwar strategic game. Our experimental results show that the system model is able to learn various forms of knowledge for the different domain tasks. The results also confirms that the memory interaction can lead to a significant improvement in both learning efficiency and performance.en
dc.format.extent175 p.en
dc.language.isoenen
dc.subjectDRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligenceen
dc.titleNeural modeling of multiple memory systems and learningen
dc.typeThesisen
dc.contributor.supervisorTan Ah Hweeen
dc.contributor.schoolSchool of Computer Engineeringen
dc.description.degreeDOCTOR OF PHILOSOPHY (SCE)en
dc.contributor.researchCentre for Computational Intelligenceen
dc.identifier.doi10.32657/10356/62219en
item.grantfulltextopen-
item.fulltextWith Fulltext-
Appears in Collections:SCSE Theses
Files in This Item:
File Description SizeFormat 
Copy of PpMain.pdfMain article2.35 MBAdobe PDFThumbnail
View/Open

Page view(s) 50

327
Updated on Aug 2, 2021

Download(s) 20

141
Updated on Aug 2, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.