UPM Institutional Repository

FASTA-ELM: a fast adaptive shrinkage/thresholding algorithm for extreme learning machine and its application to gender recognition


Citation

Mahmood, Saif F. and Marhaban, Mohammad Hamiruce and Rokhani, Fakhrul Zaman and Samsudin, Khairulmizam and Arigbabu, Olasimbo Ayodeji (2017) FASTA-ELM: a fast adaptive shrinkage/thresholding algorithm for extreme learning machine and its application to gender recognition. Neurocomputing, 219. 312 - 322. ISSN 0925-2312; ESSN: 1872-8286

Abstract

Extreme learning machine (ELM) is an interesting algorithm for learning the hidden layer of single layer feed forward neural networks. However, one of the main shortcomings restricting further improvement of ELM is the complexity of singular value decomposition (SVD) for computing the Moore-Penrose generalized inverse of the hidden layer matrix. This paper presents a new algorithm named fast adaptive shrinkage/thresholding algorithm ELM (FASTA-ELM) which uses an extension of forward-backward splitting (FBS) to compute the smallest norm of the output weights in ELM. The proposed FASTA-ELM algorithm is evaluated on face gender recognition problem using 5 benchmarked datasets. The results indicate that FASTA-ELM provides efficient performance and outperforms the standard ELM and two other variants of ELM in terms of generalization ability and computational time. Furthermore, the recognition performance of FASTA-ELM is comparable to other state-of-the-art face gender recognition methods.


Download File

[img]
Preview
Text
A fast adaptive shrinkage.pdf

Download (8kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.1016/j.neucom.2016.09.046
Publisher: Elsevier
Keywords: Fast adaptive shrinkage/thresholding; Extreme learning machine; Hidden node selection; Feature representation; Face gender recognition
Depositing User: Nurul Ainie Mokhtar
Date Deposited: 25 Feb 2019 03:28
Last Modified: 25 Feb 2019 03:28
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1016/j.neucom.2016.09.046
URI: http://psasir.upm.edu.my/id/eprint/61871
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item