Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection

We implement genetic algorithm based predictive model building as an alternative to the traditional stepwise regression. We then employ the Information Complexity Measure (ICOMP) as a measure of model fitness instead of the commonly used measure of R-square. Furthermore, we propose some modification...

Descripción completa

Detalles Bibliográficos
Autores principales: Akman, Olcay, Hallam, Joshua W.
Formato: Texto
Lenguaje:English
Publicado: Frontiers Research Foundation 2010
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2906215/
https://www.ncbi.nlm.nih.gov/pubmed/20661297
http://dx.doi.org/10.3389/fnins.2010.00033
_version_ 1782184014456553472
author Akman, Olcay
Hallam, Joshua W.
author_facet Akman, Olcay
Hallam, Joshua W.
author_sort Akman, Olcay
collection PubMed
description We implement genetic algorithm based predictive model building as an alternative to the traditional stepwise regression. We then employ the Information Complexity Measure (ICOMP) as a measure of model fitness instead of the commonly used measure of R-square. Furthermore, we propose some modifications to the genetic algorithm to increase the overall efficiency.
format Text
id pubmed-2906215
institution National Center for Biotechnology Information
language English
publishDate 2010
publisher Frontiers Research Foundation
record_format MEDLINE/PubMed
spelling pubmed-29062152010-07-26 Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection Akman, Olcay Hallam, Joshua W. Front Neurosci Neuroscience We implement genetic algorithm based predictive model building as an alternative to the traditional stepwise regression. We then employ the Information Complexity Measure (ICOMP) as a measure of model fitness instead of the commonly used measure of R-square. Furthermore, we propose some modifications to the genetic algorithm to increase the overall efficiency. Frontiers Research Foundation 2010-07-08 /pmc/articles/PMC2906215/ /pubmed/20661297 http://dx.doi.org/10.3389/fnins.2010.00033 Text en Copyright © 2010 Akman and Hallam. http://www.frontiersin.org/licenseagreement This is an open-access article subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited.
spellingShingle Neuroscience
Akman, Olcay
Hallam, Joshua W.
Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title_full Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title_fullStr Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title_full_unstemmed Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title_short Natural Selection at Work: An Accelerated Evolutionary Computing Approach to Predictive Model Selection
title_sort natural selection at work: an accelerated evolutionary computing approach to predictive model selection
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2906215/
https://www.ncbi.nlm.nih.gov/pubmed/20661297
http://dx.doi.org/10.3389/fnins.2010.00033
work_keys_str_mv AT akmanolcay naturalselectionatworkanacceleratedevolutionarycomputingapproachtopredictivemodelselection
AT hallamjoshuaw naturalselectionatworkanacceleratedevolutionarycomputingapproachtopredictivemodelselection

Ejemplares similares