Logo

CIRG - Research  -  Neural Networks 



[Bullet] Home
About
News
[Bullet]

- NN
- DM
- SI
- EC
- MAS
- AIS
- IA
- Bioinf
- Games
- Opt
- FA
- Industry

Publications
People
Resources
Links
Contact Us

OVERVIEW

The focus of the neural networks group is to investigate aspects of training and optimization of neural networks, and to apply neural networks to solve real-world problems. The activities of this focus area are mainly centered around architecture selection, active learning, and the development of new an efficient training algorithms. Some work is done on self-organizing maps.

Current applications are directed towards data mining, spam detection, user authentication, fraud detection, gesture recognition, and trading on financial markets. Applications of self-organization maps to exploratory data analysis, data mining, and species identification are done.

ACTIVE MEMBERS

List the current members actively doing research in this focus area. [ Show ]

ALUMNI MEMBERS

S van der Stockt

M.Sc Completed in 2008

E Dean

M.Sc Started in 2002

J Pun

M.Sc Completed

E Clements

Hons-B.Sc Completed in 2003

U Paquet

M.Sc Completed in 2003

R van den Hoven

Hons-B.Sc Completed in 2003

A Ismail

PhD Started in 2005
M.Sc Completed in 2001

A Adejumo

M.Sc Completed in 1999

GROUP PUBLICATIONS

List publications of this research focus area. [ Show ]

MEMBER PROFILE



 Name:

 Adebola Adejumo

Portrait photo

 E-mail:

 engel@cs.up.ac.za

 Group(s):

 Neural Networks

 

 Degree specific information: M.Sc

 Title:

 Active Learning Algorithms for Multilayer Feedforward Neural Networks

 Abstract:

Backpropagation has played a vital role in the resurgence of interest in artificial neural networks. Eversince, a lot of research effort concentrated on finding ways to improve its performance. Active learning has emerged as an efficient alternative to improve the performance of multilayer feedforward neural networks. The learner is given active control over the information to include in the training set, and in doing so, the generalization accuracy is improved and the computational cost and complexity of the network are reduced compared to training on a fixed set of data. While many research effort has been invested in designing new learning approaches, an elaborate comparison of active learning approaches is still lacking. The objective of this research study is to compare and critisize learning approaches and also to propose a new selective learning algorithm. This work presents a comparison of four selected active learning algorithms.

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Not available for download yet.




You are visitor #16382
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