Title :
The probably approximately correct (PAC) population size of a genetic algorithm
Author :
Hernandez-Aguirre, Arturo ; Buckles, Bill P. ; Martinez-Alcántara, Antonio
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Tulane Univ., New Orleans, LA, USA
Abstract :
Probably approximately correct learning, PAC-learning, is a framework for the study of learnability and learning machines. In this framework, learning is induced through a set of examples. The size of this set is such that with probability greater than 1-δ the learning machine shows an approximately correct behavior with error no greater than ε. The authors use the PAC framework to derive the size of a GA population that with probability 1-δ contains at least one individual ε-close to a target hypothesis or solution
Keywords :
genetic algorithms; learning by example; probability; GA population; PAC framework; PAC population size; PAC-learning; approximately correct behavior; genetic algorithm; learnability; learning machines; probably approximately correct; Error correction; Genetic algorithms; Machine learning; Terminology;
Conference_Titel :
Tools with Artificial Intelligence, 2000. ICTAI 2000. Proceedings. 12th IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7695-0909-6
DOI :
10.1109/TAI.2000.889870
