Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/62219
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Wenwen | en |
dc.date.accessioned | 2015-02-27T04:06:36Z | en |
dc.date.available | 2015-02-27T04:06:36Z | en |
dc.date.copyright | 2015 | en |
dc.date.issued | 2015 | en |
dc.identifier.citation | Wang, W. (2015). Neural modeling of multiple memory systems and learning. Doctoral thesis, Nanyang Technological University, Singapore. | en |
dc.identifier.uri | https://hdl.handle.net/10356/62219 | en |
dc.description.abstract | This 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.extent | 175 p. | en |
dc.language.iso | en | en |
dc.subject | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence | en |
dc.title | Neural modeling of multiple memory systems and learning | en |
dc.type | Thesis | en |
dc.contributor.supervisor | Tan Ah Hwee | en |
dc.contributor.school | School of Computer Engineering | en |
dc.description.degree | DOCTOR OF PHILOSOPHY (SCE) | en |
dc.contributor.research | Centre for Computational Intelligence | en |
dc.identifier.doi | 10.32657/10356/62219 | en |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
Appears in Collections: | SCSE Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Copy of PpMain.pdf | Main article | 2.35 MB | Adobe PDF | View/Open |
Page view(s) 50
481
Updated on Mar 26, 2024
Download(s) 20
237
Updated on Mar 26, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.