You are not logged in.
Openly accessible

Mixed transfer function neural networks for knowledge acquistition

Khan, M. Imad, Frayman, Yakov and Nahavandi, Saeid 2009, Mixed transfer function neural networks for knowledge acquistition, in ICIT 2009 : Future technology in service of regional industry : Proceedings of the IEEE Industrial Tecnology 2009 international conference, IEEE, Piscataway, N. J., pp. 1-6, doi: 10.1109/ICIT.2009.4939662.

Attached Files
Name Description MIMEType Size Downloads
SYMPLECTIC-LICENCE Symplectic Licence Click to show the corresponding preview/stream 1.47KB 9
nahavandi-mixedtransferfunction-2009.pdf Published version application/pdf 260.53KB 196

Title Mixed transfer function neural networks for knowledge acquistition
Author(s) Khan, M. Imad
Frayman, Yakov
Nahavandi, SaeidORCID iD for Nahavandi, Saeid orcid.org/0000-0002-0360-5270
Conference name IEEE Industrial Technology. International Conference (2009 : Gippsland, Victoria)
Conference location Gippsland, Victoria
Conference dates 10 - 13 Feb. 2009
Title of proceedings ICIT 2009 : Future technology in service of regional industry : Proceedings of the IEEE Industrial Tecnology 2009 international conference
Editor(s) [Unknown]
Publication date 2009
Conference series IEEE Industrial Technology International Conference
Start page 1
End page 6
Total pages 6
Publisher IEEE
Place of publication Piscataway, N. J.
Keyword(s) inductive modeling
neural networks
mixed transfer functions
over-fitting
model complexity
Summary Modeling helps to understand and predict the outcome of complex systems. Inductive modeling methodologies are beneficial for modeling the systems where the uncertainties involved in the system do not permit to obtain an accurate physical model. However inductive models, like artificial neural networks (ANNs), may suffer from a few drawbacks involving over-fitting and the difficulty to easily understand the model itself. This can result in user reluctance to accept the model or even complete rejection of the modeling results. Thus, it becomes highly desirable to make such inductive models more comprehensible and to automatically determine the model complexity to avoid over-fitting. In this paper, we propose a novel type of ANN, a mixed transfer function artificial neural network (MTFANN), which aims to improve the complexity fitting and comprehensibility of the most popular type of ANN (MLP - a Multilayer Perceptron).
Notes ©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
ISBN 9781424435050
Language eng
DOI 10.1109/ICIT.2009.4939662
Field of Research 080602 Computer-Human Interaction
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2009, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30029265

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 623 Abstract Views, 207 File Downloads  -  Detailed Statistics
Created: Fri, 11 Jun 2010, 20:30:44 EST by facadmin

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.