DocumentCode :
3425338
Title :
Self bounding genetic algorithms for machine learning
Author :
Lozano, Fernando ; Koltchinskii, Vladimir
Author_Institution :
Departmento de Ingenieria Electrica y Electronica, Univ. de los Andes, Bogota, Colombia
fYear :
2005
fDate :
15-17 Dec. 2005
Abstract :
We propose an abstract self bounding genetic algorithm that can be applied to various problems of machine learning. The bound on the generalization error that is output by our algorithm is based on Rademacher penalization, a data driven penalization technique. We prove probabilistic oracle inequalities for the theoretical risk of the estimators based on this approach. This is done by comparing the performance of an idealized genetic algorithm that uses a fitness function based on the generalization error with that of an empirical genetic algorithm based on Rademacher penalization. The inequalities indicate that although we are not able to implement the idealized algorithm (because of the inability to compute the generalization error), the empirical algorithm does almost as well as the idealized algorithm would.
Keywords :
generalisation (artificial intelligence); genetic algorithms; learning (artificial intelligence); self-adjusting systems; Rademacher penalization; data driven penalization; generalization error; idealized algorithm; machine learning; probabilistic oracle inequality; self bounding genetic algorithm; Algorithm design and analysis; Genetic algorithms; Machine learning; Machine learning algorithms; Mathematics; Network topology; Neural networks; Process design; Statistics; Virtual colonoscopy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Applications, 2005. Proceedings. Fourth International Conference on
Print_ISBN :
0-7695-2495-8
Type :
conf
DOI :
10.1109/ICMLA.2005.57
Filename :
1607473
Link To Document :
بازگشت