NWU Institutional Repository

A comparison of generalization techniques on supervised chess evaluation functions

dc.contributor.advisorVan Vuuren, P.A.en_US
dc.contributor.advisorAlberts, A.J.en_US
dc.contributor.authorSwart, W.P.en_US
dc.contributor.researchID10732926 - Van Vuuren, Pieter Andries (Supervisor)en_US
dc.contributor.researchID12429414 - Alberts, Andreas Jacobus (Supervisor)en_US
dc.date.accessioned2021-11-09T14:09:00Z
dc.date.available2021-11-09T14:09:00Z
dc.date.issued2021en_US
dc.descriptionMEng (Computer and Electronic Engineering), North-West University, Potchefstroom Campus
dc.description.abstractThis dissertation was created in pursuit of comparing different deep neural network general-ization techniques on neural networks that were trained by supervised optimisation to be used as chess evaluation functions. Investigations were performed on training material, network anatomy and on specialized generalization techniques. These experiments were evaluated firstly as normal classifiers, and then as part of a fully fledged chess agent. It was found that deep convolutional neural networks perform exceptionally well in both of the criteria men-tioned, but that their hyperparameters may be harder to optimize. A strong correlation be-tween classifier performance and chess prowess was also noted, suggesting that classification metrics can in a broad sense be used as a gauge of chess performance.
dc.description.thesistypeMastersen_US
dc.identifier.urihttps://orcid.org/0000-0003-3674-6560en_US
dc.identifier.urihttp://hdl.handle.net/10394/37758
dc.language.isoenen_US
dc.publisherNorth-West University (South Africa)en_US
dc.subjectChess
dc.subjectDeep Neural Networks
dc.subjectSupervised Learning
dc.subjectGeneralization
dc.titleA comparison of generalization techniques on supervised chess evaluation functionsen_US
dc.typeThesisen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Swart_WP.pdf
Size:
723.37 KB
Format:
Adobe Portable Document Format
Description:

Collections