计算机应用与软件2016，Vol.33Issue(8)：242-245,272,5.DOI:10.3969/j.issn.1000-386x.2016.08.054
基于云推理的协方差矩阵自适应进化策略算法
IMPROVED CMA-ES ALGORITHM BASED ON CLOUD REASONING
摘要
Abstract
In order to overcome the shortcomings of covariance matrix adaptation evolution strategy (CMA-ES)such as premature conver-gence and low precision when being used in some optimisation problems,by making use of the good ability of cloud model in dealing with un-certainty problems,we improve the step-size control process of CMA-ES and find a cloud reasoning-based improved CMA-ES algorithm.After building the cloud reasoning model of step-size control,the improved algorithm achieves step-size control by using uncertainty reasoning of cloud model,and avoids the deficiency of original algorithm that it uses deterministic function mapping for step-size scale but ignores the un-certainty in evolution process.Finally,through test functions we verify that the improved algorithm has higher optimisation performance.关键词
协方差矩阵自适应进化策略/云推理/步长控制/全局优化Key words
Covariance matrix adaptation evolution strategy (CMA-ES)/Cloud reasoning/Step-size control/Global optimisation分类
信息技术与安全科学引用本文复制引用
乔帅,续欣莹,阎高伟..基于云推理的协方差矩阵自适应进化策略算法[J].计算机应用与软件,2016,33(8):242-245,272,5.基金项目
国家自然科学基金项目（61450011）；山西省自然科学基金项目（2011011012－2）。 （）
