Multi hidden layer extreme learning machine optimised with batch intrinsic plasticity
Accession number: 20191706826940
Authors: Pang, Shan 1   ; Yang, Xinyi 2  
Author affiliations : 1 College of Information and Electrical Engineering, Ludong University, Yantai; 264025, China
2 Department of Aircraft Engineering, Naval Aeronautical and Astronautical University, Yantai; 264001, China
Corresponding author: Pang, Shan (pangshanpp@163.com)
Source title: International Journal of Computational Science and Engineering
Abbreviated source title: Int. J. Comput. Sci. Eng.
Volume: 18
Issue: 4
Issue date: 2019
Publication Year: 2019
Pages: 375-382
Language: English
ISSN: 17427185
E-ISSN: 17427193
Document type: Journal article (JA)
Publisher: Inderscience Enterprises Ltd.
Abstract: Extreme learning machine (ELM) is a novel learning algorithm where the training is restricted to the output weights to achieve a fast learning speed. However, ELM tends to require more neurons in the hidden layer and sometimes leads to ill-condition problem due to random selection of input weights and hidden biases. To address these problems, we propose a multi hidden layer extreme learning machine optimised with batch intrinsic plasticity (BIP) scheme. The proposed algorithm has a deep structure and thus learns features more efficiently. The combination of BIP scheme helps to achieve better generalisation ability. Comparisons with some state-of-the-art ELM algorithms on both regression and classification problems have verified the performance and effectiveness of our proposed algorithm.
Copyright © 2019 Inderscience Enterprises Ltd.
Number of references: 24
Main heading: Learning algorithms
Controlled terms: Knowledge acquisition -  Learning systems -  Network layers -  Neural networks
Uncontrolled terms: Deep structure -  Extreme learning machine -  Generalisation -  Hidden layers -  Ill-conditions -  Intrinsic plasticity -  Random selection -  State of the art
Classification code: 723Computer Software, Data Handling and Applications  -  723.4Artificial Intelligence
DOI: 10.1504/IJCSE.2019.099075，

已检索。已发到你指定邮箱

速度真快👍 @怕哦哦哦