中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Multi-objective Artificial Bee Colony Algorithm with Information Learning for Model Optimization of Extreme Learning Machine

文献类型:会议论文

作者Zhang H(张浩); Zhang DY(张丁一); Ku T(库涛)
出版日期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
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.

入库方式: OAI收割

来源:沈阳自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。