Authors:
Cruz Enrique Borges Hernández

Abstract:

We propose a tool for controlling the complexity of Genetic Programming models. The tool is supported by the theory of Vapnik-Chervonekis dimension (VCD) and is combined with a novel representation of models named straight line program. Experimental results, implemented on conventional algebraic structures (such as polynomials), show that the empirical risk, penalized by suitable upper bounds for the Vapnik-Chervonenkis dimension, gives a generalization error smaller than the use of statistical conventional techniques such as Bayesian or Akaike information criteria.



Published in: Computational Intelligence
Volume:

613


Pages:

105-120


Year:

2016


Citations:
Citation
Cruz Enrique Borges Hernández. (2016) "Genetic Programming Model Regularization" In Computational Intelligence . vol. 613. p. 105-120. DOI: 10.1007/978-3-319-23392-5_6.