- author = "Jan Zegklitz and Petr Posik",
- title = "Model Selection and Overfitting in Genetic Programming: Empirical Study",
- booktitle = "GECCO Companion '15: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation",
- year = "2015",
- editor = "Sara Silva and Anna I Esparcia-Alcazar and Manuel Lopez-Ibanez and Sanaz Mostaghim and Jon Timmis and Christine Zarges and Luis Correia and Terence Soule and Mario Giacobini and Ryan Urbanowicz and Youhei Akimoto and Tobias Glasmachers and Francisco {Fernandez de Vega} and Amy Hoover and Pedro Larranaga and Marta Soto and Carlos Cotta and Francisco B. Pereira and Julia Handl and Jan Koutnik and Antonio Gaspar-Cunha and Heike Trautmann and Jean-Baptiste Mouret and Sebastian Risi and Ernesto Costa and Oliver Schuetze and Krzysztof Krawiec and Alberto Moraglio and Julian F. Miller and Pawel Widera and Stefano Cagnoni and JJ Merelo and Emma Hart and Leonardo Trujillo and Marouane Kessentini and Gabriela Ochoa and Francisco Chicano and Carola Doerr",
- isbn13 = "978-1-4503-3488-4",
- keywords = "genetic algorithms, genetic programming: Poster",
- pages = "1527--1528",
- month = "11-15 " # jul,
- organisation = "SIGEVO",
- address = "Madrid, Spain",
-
URL = "
http://doi.acm.org/10.1145/2739482.2764678",
-
DOI = "
doi:10.1145/2739482.2764678",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
-
abstract = "Genetic Programming has been very successful in
solving a large area of problems but its use as a
machine learning algorithm has been limited so far. One
of the reasons is the problem of over-fitting which
cannot be solved or suppressed as easily as in more
traditional approaches. Another problem, closely
related to over fitting, is the selection of the final
model from the population.
In this article we present our research that addresses both problems: over fitting and model selection. We compare several ways of dealing with over fitting, based on Random Sampling Technique (RST) and on using a validation set, all with an emphasis on model selection. We subject each approach to a thorough testing on artificial and real--world datasets and compare them with the standard approach, which uses the full training data, as a baseline.",
- notes = "Also known as \cite{2764678} Distributed at GECCO-2015.",
