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 nahavandi-mixedtransferfunction-2009.pdf Published version application/pdf 260.53KB 278 Title Mixed transfer function neural networks for knowledge acquistition Author(s) Khan, M. Imad Frayman, Yakov 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 Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30029265 Document type: Conference Paper Collections: Institute for Intelligent Systems Research and Innovation (IISRI) Institute for Technology Research and Innovation Open Access Collection GTP Research Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     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 Fri, 11 Jun 2010, 20:30:47 EST Fri, 11 Jun 2010, 20:37:59 EST Fri, 11 Jun 2010, 20:38:44 EST Mon, 14 Jun 2010, 08:27:17 EST Mon, 14 Jun 2010, 11:50:49 EST Mon, 14 Jun 2010, 11:52:56 EST Mon, 14 Jun 2010, 12:41:51 EST Mon, 28 Jun 2010, 16:35:39 EST Mon, 28 Jun 2010, 19:21:18 EST Wed, 08 Sep 2010, 10:49:21 EST Fri, 16 Mar 2012, 18:09:04 EST Wed, 02 Jul 2014, 11:15:44 EST Wed, 02 Jul 2014, 11:16:24 EST Mon, 21 Jul 2014, 10:29:03 EST Fri, 17 Oct 2014, 10:25:07 EST Wed, 21 Oct 2015, 17:03:45 EST Tue, 17 Nov 2015, 14:15:50 EST Tue, 06 Sep 2016, 15:39:03 EST Tue, 05 Dec 2017, 09:16:18 EST Fri, 07 Sep 2018, 14:59:49 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 1 times in Scopus Search Google Scholar Access Statistics: 939 Abstract Views, 291 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.