学术讲座-Surrogate-assisted Meta-heuristic Optimization for Computationally Expensive Problems
发布者: 科研处 更新日期: 2018-01-12 访问次数: 27

举办单位:信息科学与工程学院

讲座题目

Surrogate-assisted   Meta-heuristic Optimization for Computationally Expensive Problems

讲 座 人

孙超利

讲座人

职称、职务

教授

主持人

潘正祥

讲座类型

R自然科学

讲座对象

全校师生

举办时间

20181128:00-1000

□社会科学

举办地点

C1-206

Chaoli Sun received her B.Sc. And   M.Sc. Degrees in Computer Application Technology from Hohai University,   Nanjing, Jiangsu, China, and Ph.D. in Mechanical Design and Theory from   Taiyuan University of Science and Technology, Taiyuan,Shanxi, China, in 2011.   She is a Professor in the Department of Computer Science and Technology,   Taiyuan University of Science and Technology. She was a   Research Fellow with the Department of Computer Science, University of   Surrey, working on an EU grant on SWARM_ORGAN from September 2014 to   September 2016. Her main research interests include swarm intelligence and   swarm robotics, surrogate-assisted swarm optimization, large-scale swarm   optimization, and optimization of complex mechanical systems.

She is a member of the   Evolutionary Computation Technical Committee of the IEEE Computational   Intelligence Society, an Associate Editor of Soft Computing(Springer) and an   Editorial Board Member of Complex& Intelligence System Intelligence   Society, an Associate Editor of Soft Computing. Dr. Sun has published more   than 30 papers as the first author in international journals and conferences.

讲座

主要内容

Meta-heuristic algorithms have been shown to be   powerful in optimization of engineering problems. However, a large number of   fitness evaluations are required before locating near at the global optimum,   which limits the application of meta-heuristic algorithm in solving   computational expensive problems. In this topic, a new fitness estimation   strategy, which was proposed to approximate the fitness value of individuals   based on the positional relationship between individuals, will be firstly   introduced. Then a surrogate-assisted cooperative swarm optimization   algorithm will be given subsequently for solving high-dimensional   computationally expensive problems, in which a surrogate-assisted   particle  swarm optimization(PSO)   algorithm and a surrogate-assisted social learning-based PSO(SL-PSO)   algorithm cooperatively search for the global optimum, where two algorithms   share promising solutions evaluated by the real fitness function.


打印此页】 【顶部】 【关闭窗口