The Probably Approximately Correct (PAC) population size of a genetic algorithm

被引：7

作者：

Hernández-Aguirre, A ^{[1
]}

Buckles, BP ^{[1
]}

Martinez-Alcántara, A ^{[1
]}

机构：

[1] Tulane Univ, Dept Elect Engn & Comp Sci, New Orleans, LA 70118 USA

来源：

12TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS | 2000年

关键词：

D O I：

10.1109/TAI.2000.889870

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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-delta the learning machine shows an approximately correct behavior with error no greater than epsilon. in this paper we use the PAC framework to derive the size of a CA population that with probability 1-delta contains at least one individual epsilon -close to a target hypothesis or solution.

引用

页码：199 / 202

页数：4