Please use this identifier to cite or link to this item:
Title: Extreme learning machine with affine transformation inputs in an activation function
Authors: Cao, Jiuwen
Zhang, Kai
Yong, Hongwei
Lai, Xiaoping
Chen, Badong
Lin, Zhiping
Keywords: Engineering::Electrical and electronic engineering
Engineering::Computer science and engineering
Issue Date: 2018
Source: Cao, J., Zhang, K., Yong, H., Lai, X., Chen, B., & Lin, Z. (2019). IEEE Transactions on Neural Networks and Learning Systems, 30(7), 2093-2107. doi:10.1109/TNNLS.2018.2877468
Journal: IEEE Transactions on Neural Networks and Learning Systems
Abstract: The extreme learning machine (ELM) has attracted much attention over the past decade due to its fast learning speed and convincing generalization performance. However, there still remains a practical issue to be approached when applying the ELM: the randomly generated hidden node parameters without tuning can lead to the hidden node outputs being nonuniformly distributed, thus giving rise to poor generalization performance. To address this deficiency, a novel activation function with an affine transformation (AT) on its input is introduced into the ELM, which leads to an improved ELM algorithm that is referred to as an AT-ELM in this paper. The scaling and translation parameters of the AT activation function are computed based on the maximum entropy principle in such a way that the hidden layer outputs approximately obey a uniform distribution. Application of the AT-ELM algorithm in nonlinear function regression shows its robustness to the range scaling of the network inputs. Experiments on nonlinear function regression, real-world data set classification, and benchmark image recognition demonstrate better performance for the AT-ELM compared with the original ELM, the regularized ELM, and the kernel ELM. Recognition results on benchmark image data sets also reveal that the AT-ELM outperforms several other state-of-the-art algorithms in general.
ISSN: 2162-237X
DOI: 10.1109/TNNLS.2018.2877468
Rights: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Extreme Learning Machine With Affine Transformation Inputs in an Activation Function.pdf1.13 MBAdobe PDFView/Open

Citations 10

Updated on Jan 29, 2023

Web of ScienceTM
Citations 10

Updated on Jan 29, 2023

Page view(s)

Updated on Feb 4, 2023

Download(s) 20

Updated on Feb 4, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.