- author = "Michael J. Cavaretta and Kumar Chellapilla",
- title = "Data Mining using Genetic Programming: The Implications of Parsimony on Generalization Error",
- booktitle = "Proceedings of the Congress on Evolutionary Computation",
- year = "1999",
- editor = "Peter J. Angeline and Zbyszek Michalewicz and Marc Schoenauer and Xin Yao and Ali Zalzala",
- volume = "2",
- pages = "1330--1337",
- address = "Mayflower Hotel, Washington D.C., USA",
- publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331, USA",
- month = "6-9 " # jul,
- organisation = "Congress on Evolutionary Computation, IEEE / Neural Networks Council, Evolutionary Programming Society, Galesia, IEE",
- publisher = "IEEE Press",
- keywords = "genetic algorithms, genetic programming, data mining, GP-variant, common dataset, data mining heuristic, generalisation error, less complex models, program complexity, training error, unseen data, computational complexity, data mining, generalisation (artificial intelligence)",
- ISBN = "0-7803-5536-9 (softbound)",
- ISBN = "0-7803-5537-7 (Microfiche)",
-
DOI = "
doi:10.1109/CEC.1999.782602",
- size = "8 pages",
- abstract = "A common data mining heuristic is, 'when choosing between models with the same training error, less complex models should be preferred as they perform better on unseen data'. This heuristic may not always hold. In genetic programming a preference for less complex models is implemented as: (i) placing a limit on the size of the evolved program; (ii) penalising more complex individuals, or both. The paper presents a GP-variant with no limit on the complexity of the evolved program that generates highly accurate models on a common dataset",
-
notes = "statlog
CEC-99 - A joint meeting of the IEEE, Evolutionary Programming Society, Galesia, and the IEE.
Library of Congress Number = 99-61143",
