Multi-objective optimization of extreme learning machine using physical programming

科研成果: 书/报告/会议事项章节会议稿件同行评审

2 引用 (Scopus)

摘要

Feedforward neural networks have been widely used in various fields, such as disease detection, object tracking, and nonlinear prediction. The performance objectives which are required in different practical problems are also different. It is an issue that how to select the neural network structure to meet the requirement of the designer. This paper presents an algorithm called physical programming (PP) which optimizes multiple performance objectives of networks by selecting the number of hidden nodes and the activation function for extreme learning machine (ELM). In PP, designer's expectations for each objective are divided: unacceptable, highly undesirable, undesirable, tolerable, desirable, and highly desirable, of which the value ranges are decided based on the actual situation and designer's preferences. And then the designer seeks the optimized network structure by genetic algorithm (GA). The simulation result shows that the optimized ELM realizes multi-objective optimization.

源语言英语
主期刊名Proceedings of the 35th Chinese Control Conference, CCC 2016
编辑Jie Chen, Qianchuan Zhao, Jie Chen
出版商IEEE Computer Society
3618-3623
页数6
ISBN(电子版)9789881563910
DOI
出版状态已出版 - 26 8月 2016
活动35th Chinese Control Conference, CCC 2016 - Chengdu, 中国
期限: 27 7月 201629 7月 2016

出版系列

姓名Chinese Control Conference, CCC
2016-August
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议35th Chinese Control Conference, CCC 2016
国家/地区中国
Chengdu
时期27/07/1629/07/16

指纹

探究 'Multi-objective optimization of extreme learning machine using physical programming' 的科研主题。它们共同构成独一无二的指纹。

引用此

Xu, Y., Yao, F., Chai, S., & Sun, L. (2016). Multi-objective optimization of extreme learning machine using physical programming. 在 J. Chen, Q. Zhao, & J. Chen (编辑), Proceedings of the 35th Chinese Control Conference, CCC 2016 (页码 3618-3623). 文章 7553915 (Chinese Control Conference, CCC; 卷 2016-August). IEEE Computer Society. https://doi.org/10.1109/ChiCC.2016.7553915