摘要
借鉴信息传递的概率模型,提出一种求解非数值优化问题的新的分布估计算法.首先根据进化过程中的优良信息建立一个不断更新的先验知识概率模型,以相邻符号出现的频率为基础建立条件传递概率模型,然后通过二者的结合建立了一种后验概率模型并用以指导产生新群体.针对旅行商问题进行的仿真试验表明本文算法可较好地改善分布估计算法的早熟收敛现象.
Reference to the probability model of information transmission,a new estimation of distribution algorithm is proposed for non numerical optimization problems.Firstly,an updating model of a priori knowledge probability is built according to the superior information produced during evolution process,and the model of conditional transfer probability is also constructed based on the emerging frequencies of neighboring symbols.Secondly,the model of posterior probability is given by combining the above mentioned probability model to guide new population generating.Finally the presented approach is tested on TSP problems,and the results show that the proposed algorithm can improve the premature convergence of estimation of distribution algorithms.
出处
《电子学报》
EI
CAS
CSCD
北大核心
2011年第4期967-970,共4页
Acta Electronica Sinica
基金
山西省青年科技基金(No.2010021017-2)
关键词
分布估计算法
信息传递
后验概率
旅行商问题
estimation of distribution algorithms
information transmission
posterior probability
TSP