Logo

CIRG - People  -  Honours Members 



[Bullet] Home
About
News
Research
Publications
[Bullet]

- Staff
- Doctorates
- Masters
- Honours

Resources
Links
Contact Us

CURRENT MEMBERS

Below is a list of the honours members actively conducting research at CIRG. Click on each name for more detailed information on the researcher and his/her project.


None


ALUMNI

Below is a list of previous honours members that conducted research at CIRG. Click on each name for more detailed information on the researcher and his/her project.


A van Wyk

M.Sc Started in 2009
Hons-B.Sc Completed in 2008

B Anguelov

M.Sc Started in 2009
Hons-B.Sc Completed in 2008

J Buys

Hons-B.Sc Completed in 2007

H de Nysschen

Hons-B.Sc Completed in 2007

M Lynch

Hons-B.Sc Completed in 2007

W Matthysen

M.Sc Started in 2008
Hons-B.Sc Completed in 2007

M Riekert

M.Sc Started in 2008
Hons-B.Sc Completed in 2007

H Roux

Hons-B.Sc Completed in 2007

J Swanepoel

Hons-B.Sc Completed in 2007

D Uys

Hons-B.Sc Completed in 2007

J van der Walt

Hons-B.Sc Completed in 2007

L Langenhoven

M.Sc Started in 2008
Hons-B.Sc Completed in 2006

S Olorunda

Hons-B.Sc Completed in 2006

J du Toit

Hons-B.Sc Completed in 2005

F Geldenhuys

Hons-B.Sc Completed in 2005

C Schutte

Hons-B.Sc Completed in 2005

P van der Merwe

Hons-B.Sc Completed in 2005

J Conradie

Hons-B.Sc Completed in 2004

S Allen

M.Sc Started in 2005
Hons-B.Sc Completed in 2004

H Grobler

M.Sc Completed in 2005
Hons-B.Sc Completed in 2004

G Pampara

M.Sc Started in 2005
Hons-B.Sc Completed in 2004

G Tanna

Hons-B.Sc Completed in 2004

E van Loggerenberg

M.Sc Started in 2005
Hons-B.Sc Completed in 2004

C Coetser

Hons-B.Sc Completed in 2003

C Dubber

Hons-B.Sc Completed in 2003

D Fine

Hons-B.Sc Completed in 2003

E Papacostantis

M.Sc Started in 2004
Hons-B.Sc Completed in 2003

F Scheffer

Hons-B.Sc Completed in 2003

L Liddell

Hons-B.Sc Completed in 2003

M Drozdz

Hons-B.Sc Completed in 2003

D Barla-Szabo

M.Sc Started in 2003
Hons-B.Sc Completed in 2002

M Combrink

Hons-B.Sc Completed in 2002

E de Villiers

Hons-B.Sc Completed in 2002

C Esterhuizen

Hons-B.Sc Completed in 2002

N Franken

PhD Started in 2005
M.Sc Completed in 2004
Hons-B.Sc Completed in 2002

H Kunzman

Hons-B.Sc Completed in 2002

C Naicker

PhD Started in 2007
M.Sc Completed in 2006
Hons-B.Sc Completed in 2002

D Naude

Hons-B.Sc Completed in 2002

G Potgieter

M.Sc Completed in 2003
Hons-B.Sc Completed in 2001

G Bijker

Hons-B.Sc Completed in 2000

HW Botha

Hons-B.Sc Completed in 2000

R Brits

M.Sc Completed in 2003
Hons-B.Sc Completed in 2000

F du Toit

Hons-B.Sc Completed in 2000

B Badenhorst

Hons-B.Sc Completed in 2000

JC Welgemoed

Hons-B.Sc Completed in 1999

RNM Minnaar

Hons-B.Sc Completed in 1998

E Basson

M.Sc Started in 1999
Hons-B.Sc Completed in 1998

MEMBER PROFILE



 Name:

 Nelis Franken

Portrait photo

 E-mail:

 nfranken@cs.up.ac.za

 Group(s):

 Evolutionary Computation
 Swarm Intelligence
 Games

 

 Degree specific information: PhD

 Title:

 Variable Length Particles for PSO

 Abstract:

Not available

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Not available for download yet.

 

 Degree specific information: M.Sc

 Title:

 PSO-Based Coevolutionary Game Learning

 Abstract:

Games have been investigated as computationally complex problems since the inception of artificial intelligence in the 1950's. Originally, search-based techniques were applied to create a competent (and sometimes even expert) game player. The search-based techniques, such as game trees, made use of human-defined knowledge to evaluate the current game state and recommend the best move to make next. Recent research has shown that neural networks can be evolved as game state evaluators, thereby removing the human intelligence factor completely. This study builds on the initial research that made use of evolutionary programming to evolve neural networks in the game learning domain. Particle Swarm Optimisation (PSO) is applied inside a coevolutionary training environment to evolve the weights of the neural network. The training technique is applied to both the zero sum and non-zero sum game domains, with specific application to Tic-Tac-Toe, Checkers and the Iterated Prisoner's Dilemma (IPD). The influence of the various PSO parameters on playing performance are experimentally examined, and the overall performance of three different neighbourhood information sharing structures compared. A new coevolutionary scoring scheme and particle dispersement operator are defined, inspired by Formula One Grand Prix racing. Finally, the PSO is applied in three novel ways to evolve strategies for the IPD -- the first application of its kind in the PSO field. The PSO-based coevolutionary learning technique described and examined in this study shows promise in evolving intelligent evaluators for the aforementioned games, and further study will be conducted to analyse its scalability to larger search spaces and games of varying complexity.

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Download




You are visitor #11334
Contact webmaster
Back to top

QualNet Network Simulator University Program Valid XHTML 1.0! Valid CSS!


Computational Intelligence Research Group
University of Pretoria
Copyright © 2017