分布估计算法及其性能研究  

Research on Estimation of Distribution Algorithms Based on Probabilistic Models

作　　者：丁才昌[1] 方勃[1] 鲁小平 

机构地区：[1]武汉大学计算机学院,湖北武汉430072

出　　处：《武汉大学学报（理学版）》2005年第S2期125-128,共4页Journal of Wuhan University:Natural Science Edition

摘　　要：在传统的遗传算法中,不合适的的参数设置会降低解的质量,于是在解决一些优化问题时传统的遗传算法被分布估计算法所取代.将分布估计算法按其复杂性归纳成几种模型,分别描述了它们的实现方法和求解问题的能力和效率.In conventional Genetic Algorithms,inappropriate parameters setting may decrease the quality of the solutions.Conventional algorithms are thus replaced by Estimation of Distribution Algorithms(EDAs) in solving optimization problems.They are classified according to the complexity of the models used.Each class of the new algorithms are briefly described and the computing methods and their performance are dicussed.

关 键 词：分布估计算法 概率模型 组合优化问题 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]