Abstract
Local coupled extreme learning machine (LCELM) (Qu in Neural Comput Appl 27(1):27–33, 2016) is a recently developed variant of ELM and uses the paradigm of local coupled feed-forward neural network (LCFNN) (Sun in Neural Netw 23(1):108–113, 2010) to train an ELM model. This comment is to point out that the window function used in LCELM does not satisfy the necessary conditions of window function required by LCFNN. As a result, LCELM cannot effectively control the activation of hidden-layer node for different instances. It is possible that the improper window function can cause LCELM has the same discriminant with the basic ELM.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Solving \(\tan \left( x \right) = x\). http://blitiri.blogspot.com/2012/11/solving-tan-x-x.html.
References
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501
Qu Y (2016) Local coupled extreme learning machine. Neural Comput Appl 27(1):27–33
Sun JY (2010) Local coupled feedforward neural network. Neural Netw 23(1):108–113
Acknowledgments
We thank the editor-in-chief and three anonymous reviewers whose valuable comments and suggestions help us significantly improve this paper. This work is supported by China Postdoctoral Science Foundations (2015M572361 and 2016T90799) and National Natural Science Foundations of China (61503252).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, Wg., Zhou, X., He, Yl. et al. Comments on “Local coupled extreme learning machine”. Neural Comput & Applic 28, 631–634 (2017). https://doi.org/10.1007/s00521-016-2497-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2497-z