No Cover Image

Journal article 540 views 194 downloads

Toward deep neural networks: Mirror extreme learning machines for pattern classification

Bolin Liao, Chuan Ma, Meiling Liao, Shuai Li Orcid Logo, Zhiguan Huang

Filomat, Volume: 34, Issue: 15, Pages: 4985 - 4996

Swansea University Author: Shuai Li Orcid Logo

Check full text

DOI (Published version): 10.2298/fil2015985l

Abstract

In this paper, a novel type of feed-forward neural network with a simple structure is proposed and investigated for pattern classification. Because the novel type of forward neural network’s parameter setting is mirrored with those of the Extreme Learning Machine (ELM), it is termed the mirror extre...

Full description

Published in: Filomat
ISSN: 0354-5180 2406-0933
Published: National Library of Serbia 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa56705
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: In this paper, a novel type of feed-forward neural network with a simple structure is proposed and investigated for pattern classification. Because the novel type of forward neural network’s parameter setting is mirrored with those of the Extreme Learning Machine (ELM), it is termed the mirror extreme learning machine (MELM). For the MELM, the input weights are determined by the pseudoinverse method analytically, while the output weights are generated randomly, which are completely different from the conventional ELM. Besides, a growing method is adopted to obtain the optimal hidden-layer structure. Finally, to evaluate the performance of the proposed MELM, abundant comparative experiments based on different real-world classification datasets are performed. Experimental results validate the high classification accuracy and good generalization performance of the proposed neural network with a simple structure in pattern classification.
Keywords: Mirror extreme learning machine (MELM), Weights determination, Pseudoinverse, Pattern classification, Classification datasets
College: Faculty of Science and Engineering
Issue: 15
Start Page: 4985
End Page: 4996

Similar Items