Optimization of MLP parameters on mineral potential mapping tasks

Skabar, A. 2004, Optimization of MLP parameters on mineral potential mapping tasks, in ICOTA 2004 : Proceedings of the 6th International Conference on Optimization : Techniques and Applications, ICOTA, [Ballarat, Vic.].

Attached Files
Name Description MIMEType Size Downloads

Title Optimization of MLP parameters on mineral potential mapping tasks
Author(s) Skabar, A.
Conference name International Conference on Optimization (6th : 2004 : Ballarat, Vic.)
Conference location Ballarat, Vic.
Conference dates 9-11 Dec. 2004
Title of proceedings ICOTA 2004 : Proceedings of the 6th International Conference on Optimization : Techniques and Applications
Editor(s) Rubinov, Alex
Publication date 2004
Publisher ICOTA
Place of publication [Ballarat, Vic.]
Summary Mineral potential mapping is the process of combining a set of input maps, each representing a distinct geo-scientific variable, to produce a single map which ranks areas according to their potential to host deposits of a particular type. The maps are combined using a mapping function which must be either provided by an expert (knowledge-driven approach), or induced from sample data (data-driven approach). Current data-driven approaches using multilayer perceptrons (MLPs) to represent the mapping function have several inherent problems: they rely heavily on subjective judgment in selecting training data and are highly sensitive to this selection; they do not utilize the contextual information provided by unlabeled data; and, there is no objective interpretation of the values output by the MLP. This paper presents a novel approach which overcomes these three problems.
ISBN 1876851155
Language eng
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2004, ICOTA
Persistent URL http://hdl.handle.net/10536/DRO/DU:30005282

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 275 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Mon, 07 Jul 2008, 09:47:45 EST

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.