Skip navigation
  •  Inicio
  • UDC 
    • Cómo depositar
    • Políticas do RUC
    • FAQ
    • Dereitos de Autor
    • Máis información en INFOguías UDC
  • Percorrer 
    • Comunidades
    • Buscar por:
    • Data de publicación
    • Autor
    • Título
    • Materia
  • Axuda
    • español
    • Gallegan
    • English
  • Acceder
  •  Galego 
    • Español
    • Galego
    • English
  
Ver ítem 
  •   RUC
  • Facultade de Informática
  • Investigación (FIC)
  • Ver ítem
  •   RUC
  • Facultade de Informática
  • Investigación (FIC)
  • Ver ítem
JavaScript is disabled for your browser. Some features of this site may not work without it.

Population Subset Selection for the Use of a Validation Dataset for Overfitting Control in Genetic Programming

Thumbnail
Ver/abrir
Pazos_2019_Population_subset_selection.pdf (843.2Kb)
Use este enlace para citar
http://hdl.handle.net/2183/26190
Coleccións
  • Investigación (FIC) [1678]
Metadatos
Mostrar o rexistro completo do ítem
Título
Population Subset Selection for the Use of a Validation Dataset for Overfitting Control in Genetic Programming
Autor(es)
Rivero, Daniel
Fernández-Blanco, Enrique
Fernández-Lozano, Carlos
Pazos, A.
Data
2019-07-31
Cita bibliográfica
Rivero D, Fernandez-Blanco E, Fernandez-Lozano C, Pazos A. Population subset selection for the use of a validation dataset for overfitting control in genetic programming. J Exp Theor Artif Intell. 2020; 32(2):243-271
Resumo
[Abstract] Genetic Programming (GP) is a technique which is able to solve different problems through the evolution of mathematical expressions. However, in order to be applied, its tendency to overfit the data is one of its main issues. The use of a validation dataset is a common alternative to prevent overfitting in many Machine Learning (ML) techniques, including GP. But, there is one key point which differentiates GP and other ML techniques: instead of training a single model, GP evolves a population of models. Therefore, the use of the validation dataset has several possibilities because any of those evolved models could be evaluated. This work explores the possibility of using the validation dataset not only on the training-best individual but also in a subset with the training-best individuals of the population. The study has been conducted with 5 well-known databases performing regression or classification tasks. In most of the cases, the results of the study point out to an improvement when the validation dataset is used on a subset of the population instead of only on the training-best individual, which also induces a reduction on the number of nodes and, consequently, a lower complexity on the expressions.
Palabras chave
Genetic programming
Overfitting
Validation
Evolutionary computation
 
Versión do editor
https://doi.org/10.1080/0952813X.2019.1647562
Dereitos
This is an accepted manuscript of an articled published by Taylor & Francis in "Journal of Experimental & Theoretical Artificial Intelligence", avaliable at Taylor & Francis Online
ISSN
0952-813X

Listar

Todo RUCComunidades e colecciónsPor data de publicaciónAutoresTítulosMateriasGrupo de InvestigaciónTitulaciónEsta colecciónPor data de publicaciónAutoresTítulosMateriasGrupo de InvestigaciónTitulación

A miña conta

AccederRexistro

Estatísticas

Ver Estatísticas de uso
Sherpa
OpenArchives
OAIster
Scholar Google
UNIVERSIDADE DA CORUÑA. Servizo de Biblioteca.    DSpace Software Copyright © 2002-2013 Duraspace - Suxestións