arrow
返回

Backward-chaining evolutionary algorithms

delete2006-08-01
delete25
delete
OA
AI
R
Riccardo Poli *
W
William B. Langdon
DOI:10.1016/j.artint.2006.04.003delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Starting from some simple observations on a popular selection method in Evolutionary Algorithms (EAs)-tournament selection-we highlight a previously-unknown source of inefficiency. This leads us to rethink the order in which operations are performed within EAs, and to suggest an algorithm-the EA with efficient macro-selection-that avoids the inefficiencies associated with tournament selection. This algorithm has the same expected behaviour as the standard EA but yields considerable savings in terms of fitness evaluations. Since fitness evaluation typically dominates the resources needed to solve any non-trivial problem, these savings translate into a reduction in computer time. Noting the connection between the algorithm and rule-based systems, we then further modify the order of operations in the EA, effectively turning the evolutionary search into an inference process operating in backward-chaining mode. The resulting backward-chaining EA creates and evaluates individuals recursively, backward from the last generation to the first, using depth-first search and backtracking. It is even more powerful than the EA with efficient macro-selection in that it shares all its benefits, but it also provably finds fitter solutions sooner, i.e., it is a faster algorithm. These algorithms can be applied to any form of population based search, any representation, fitness function, crossover and mutation, provided they use tournament selection. We analyse their behaviour and benefits both theoretically, using Markov chain theory and space/time complexity analysis, and empirically, by performing a variety of experiments with standard and back-ward chaining versions of genetic algorithms and genetic programming. (C) 2006 Elsevier B.V. All rights reserved.
Keyword:
evolutionary computation
genetic algorithm
genetic programming
efficient search
backward chaining
tournament selection
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Artificial Intelligence Review 封面图
Artificial Intelligence Review
IF:
13.9
论文数:
6.1K
被引数:
1.9W

机构

暂无机构信息
引用论文

引用论文

Carotenoid identification and molecular analysis of carotenoid isomerase-encoding BrCRTISO, the candidate gene for inner leaf orange coloration in Chinese cabbage
err2015-02-07
err0
PREAI
errPeirong Li; Shujiang Zhang; Shifan Zhang; Fei Li; Hui Zhang; Xinyan Liu; Jian Wu; Xiaowu Wang; Rifei Sun
err分享
err收藏
err分享
err收藏
Sugar beet floral induction and fertility: effect of vernalization and day-length extension
err2018-11-14
err0
PREAI
errS. F. Abo-Elwafa; H. M. Abdel-Rahim; A. M. Abou-Salama; E. A. Teama
err分享
err收藏
Infrared and Raman spectra of MnS2
err1974-11-01
err0
PREAI
errJ.L. Verble; F.M. Humphrey
err分享
err收藏
学者 查看更多内容