Deakin University
Browse

File(s) under permanent embargo

Mixed transfer function neural networks for knowledge acquistition

conference contribution
posted on 2009-01-01, 00:00 authored by M. Imad Khan, Yakov Frayman, Saeid Nahavandi
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).

History

Event

IEEE Industrial Technology. International Conference (2009 : Gippsland, Victoria)

Pagination

1 - 6

Publisher

IEEE

Location

Gippsland, Victoria

Place of publication

Piscataway, N. J.

Start date

2009-02-10

End date

2009-02-13

ISBN-13

9781424435050

Language

eng

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.

Publication classification

E Conference publication; E1.1 Full written paper - refereed

Copyright notice

2009, IEEE

Title of proceedings

ICIT 2009 : Future technology in service of regional industry : Proceedings of the IEEE Industrial Tecnology 2009 international conference