基于泛函网络求解随机优化问题的EM算法  

Electromagnetism-like mechanism algorithm for solving stochastic optimization problems based on function network

作　　者：方旋[1] 孙合明[1] 

机构地区：[1]河海大学理学院,南京211100

出　　处：《信息技术》2014年第4期168-171,175,共5页Information Technology

摘　　要：研究了一类带有随机变量的不确定优化问题。为了解决这类随机优化问题,首先用随机仿真为泛函网络产生训练样本,用泛函网络逼近随机函数的均值,将随机函数的均值转为不含随机变量的确定性函数,然后用类电磁算法求解确定性函数的最优解。最后,给出一些数值例子验证了所提算法的有效性。This paper investigates a kind of uncertainty optimization problems with stochastic variables.First it uses stochastic simulation to generate training samples, then uses function networks to construct a deterministic function to approximate the expected value of an uncertain function. At last,electromagnetism-like mechanism （EM） algorithm is used to optimize the deterministic function. In the end of this paper, some numerical examples are presented to illustrate the effectiveness of the proposed algorithm.

关 键 词：类电磁机制 随机优化 随机仿真 泛函网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]