Deakin University
Browse

File(s) under permanent embargo

Optimization of MLP parameters on mineral potential mapping tasks

conference contribution
posted on 2004-01-01, 00:00 authored by Andrew Skabar
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.

History

Title of proceedings

ICOTA 2004 : Proceedings of the 6th International Conference on Optimization : Techniques and Applications

Event

International Conference on Optimization (6th : 2004 : Ballarat, Vic.)

Publisher

ICOTA

Location

Ballarat, Vic.

Place of publication

[Ballarat, Vic.]

Start date

2004-12-09

End date

2004-12-11

ISBN-10

1876851155

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2004, ICOTA

Editor/Contributor(s)

A Rubinov

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC