Logo

CIRG - People  -  Doctorates Members 



[Bullet] Home
About
News
Research
Publications
[Bullet]

- Staff
- Doctorates
- Masters
- Honours

Resources
Links
Contact Us

CURRENT MEMBERS

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


M Snyman

PhD Started in 2009

P Raharja

PhD Started in 2009

M Mtshali

PhD Started in 2009

B Kalema

PhD Started in 2009

J Grobler

PhD Started in 2009
M.Eng Completed in 2009

M Ahmad

PhD Started in 2009

T Museba

PhD Started in 2008

L Li

PhD Started in 2008

C Naicker

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

K Malan

PhD Started in 2007

M Greeff

PhD Started in 2007

B Baridam

PhD Started in 2007

MC du Plessis

PhD Started in 2006

D Constantinou

PhD Started in 2006

A Graaff

PhD Started in 2005
M.Sc Completed in 2003

N Franken

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

A Ismail

PhD Started in 2005
M.Sc Completed in 2001

ALUMNI

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


L Schoeman

PhD Completed in 2010

P Lutu

PhD Completed in 2010

S Khan

PhD Completed in 2009

D Rodic

PhD Completed in 2005
M.Sc Completed in 1999

M Omran

PhD Completed in 2005

F van den Bergh

PhD Completed in 2002

MEMBER PROFILE



 Name:

 Adiel Ismail

Portrait photo

 E-mail:

 aismail@uwc.ac.za

 Group(s):

 Swarm Intelligence
Neural Networks

 

 Degree specific information: PhD

 Title:

 Non-Parametic PSO

 Abstract:

Not available

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Not available for download yet.

 

 Degree specific information: M.Sc

 Title:

 Training and Optimization of Product Unit Neural Networks

 Abstract:

Product units in the hidden layer of multilayer neural networks provide a pwerful mechanism for neural networks to efficiently learn higher-order combinations of inputs. Training product unit neural networks using local optimization algorithms is difficult due to an increased number of local minima and increased chances of network paralysis. This research investigates the problems using local optimization, especially gradient descent, to train product unit neural networks, and shows that particle swarm optimization, genetic algorithms and leapfrog are efficient alternatives to successfully train product unit neural networks. Architecture selection, i.e. pruning, of product unit neural networks is also studied and a pruning algorithm developed.

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Download




You are visitor #154480
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