Dimensionality reduction in complex models

Abstract

As a part of the Managing Uncertainty in Complex Models (MUCM) project, research at Aston University will develop methods for dimensionality reduction of the input and/or output spaces of models, as seen within the emulator framework. Towards this end this report describes a framework for generating toy datasets, whose underlying structure is understood, to facilitate early investigations of dimensionality reduction methods and to gain a deeper understanding of the algorithms employed, both in terms of how effective they are for given types of models / situations, and also their speed in applications and how this scales with various factors. The framework, which allows the evaluation of both screening and projection approaches to dimensionality reduction, is described. We also describe the screening and projection methods currently under consideration and present some preliminary results. The aim of this draft of the report is to solicit feedback from the project team on the dataset generation framework, the methods we propose to use, and suggestions for extensions that should be considered.

Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
?? 50811700Jl ??
Uncontrolled Keywords: Methods for dimensionality reduction,dataset generation framework,wrapper methods
ISBN: NCRG/2007/001
Last Modified: 26 Dec 2023 09:54
Date Deposited: 09 Sep 2009 12:37
PURE Output Type: Technical report
Published Date: 2007-05
Authors: Boukouvalas, Alexis
Maniyar, Dharmesh M.
Cornford, Dan (ORCID Profile 0000-0001-8787-6758)

Download

Export / Share Citation


Statistics

Additional statistics for this record