loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00)
The probably approximately correct (PAC) population size of a genetic algorithm
Vancouver, British Columbia, Canada
November 13-November 15
ISBN: 0-7695-0909-6
ASCII Text
x 
 
A. Hernandez-Aguirre, B.P. Buckles, A. Martinez-Alcantara, "The probably approximately correct (PAC) population size of a genetic algorithm," Tools with Artificial Intelligence, IEEE International Conference on, pp. 0199, 12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00), 2000.
 
 
BibTex
x
 
@article{ 10.1109/TAI.2000.889870,
author = {A. Hernandez-Aguirre and B.P. Buckles and A. Martinez-Alcantara},
title = {The probably approximately correct (PAC) population size of a genetic algorithm},
journal ={Tools with Artificial Intelligence, IEEE International Conference on},
volume = {0},
year = {2000},
isbn = {0-7695-0909-6},
pages = {0199},
doi = {http://doi.ieeecomputersociety.org/10.1109/TAI.2000.889870},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Tools with Artificial Intelligence, IEEE International Conference on
TI - The probably approximately correct (PAC) population size of a genetic algorithm
SN - 0-7695-0909-6
SP
EP
A1 - A. Hernandez-Aguirre,
A1 - B.P. Buckles,
A1 - A. Martinez-Alcantara,
PY - 2000
KW - probability; genetic algorithms; learning by example; probably approximately correct; PAC population size; genetic algorithm; PAC-learning; learnability; learning machines; approximately correct behavior; PAC framework; GA population
VL - 0
JA - Tools with Artificial Intelligence, IEEE International Conference on
ER -
 
A. Hernandez-Aguirre, Dept. of Electr. Eng. & Comput. Sci., Tulane Univ., New Orleans, LA, USA
B.P. Buckles, Dept. of Electr. Eng. & Comput. Sci., Tulane Univ., New Orleans, LA, USA
A. Martinez-Alcantara, 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-/spl delta/ the learning machine shows an approximately correct behavior with error no greater than /spl epsiv/. The authors use the PAC framework to derive the size of a GA population that with probability 1-/spl delta/ contains at least one individual /spl epsiv/-close to a target hypothesis or solution.
Index Terms:
probability; genetic algorithms; learning by example; probably approximately correct; PAC population size; genetic algorithm; PAC-learning; learnability; learning machines; approximately correct behavior; PAC framework; GA population
Citation:
A. Hernandez-Aguirre, B.P. Buckles, A. Martinez-Alcantara, "The probably approximately correct (PAC) population size of a genetic algorithm," ictai, pp.0199, 12th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'00), 2000
Usage of this product signifies your acceptance of the Terms of Use.