Multi-objective Artificial Bee Colony Algorithm with Information Learning for Model Optimization of Extreme Learning Machine

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 数字工厂研究室

	Multi-objective Artificial Bee Colony Algorithm with Information Learning for Model Optimization of Extreme Learning Machine
	Zhang H(张浩); Zhang DY(张丁一); Ku T(库涛)
	2019
会议日期	November 21-23, 2018
会议地点	Singapore
关键词	Multi-objective optimization Artificial bee colony Extreme learning machine Machine learning Swarm intelligence
页码	263-272
英文摘要	As an important branch of neural networks, extreme learning machine with single-hiddenlayer feedforward have been a effective tool for regression and classification applications. However, it is difficult for ELMs to strike a balance between testing accuracy and generalization due to the random input weights and hidden biases. In this paper, a novel multi-objective optimization method of ELM based on swarm intelligence behavior is proposed to obtain good generalization ability and high testing accuracy simultaneously. The multi-objective optimization algorithm is used to select optimal input weights by minimizing this testing error and the norm of output weight. In order to improve optimal performance, an information learning method is introduced to multi-objective artificial bee colony algorithm. Experiments on four UCI data sets are conducted, and original ELM, ELM with nondominated sorting genetic algorithm and the proposed algorithm are compared. The results show that the proposed algorithm can generally obtain better generalization performance and higher accuracy with more compact network than original ELM and ELM with nondominated sorting genetic algorithm simultaneously.
产权排序	1
会议录	Proceedings of the 9th International Conference on Extreme Learning Machines (ELM2018)
会议录出版者	Springer
会议录出版地	Berlin
语种	英语
ISBN号	978-3-030-23306-8
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/26066]
专题	沈阳自动化研究所_数字工厂研究室
通讯作者	Zhang DY(张丁一)
作者单位	Shenyang Institute of Automation, Chinese Academy of Science, 114 Nanta Street, Shenyang 110016, China
推荐引用方式 GB/T 7714	Zhang H,Zhang DY,Ku T. Multi-objective Artificial Bee Colony Algorithm with Information Learning for Model Optimization of Extreme Learning Machine[C]. 见:. Singapore. November 21-23, 2018.