Random vector functional link network: Recent developments, applications, and future directions

<p>Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it results in the issues of local minima, sensitivity to...

Full description

Saved in:
Bibliographic Details
Main Author: A.K. Malik (16003193) (author)
Other Authors: Ruobin Gao (16003195) (author), M.A. Ganaie (16003198) (author), M. Tanveer (1758181) (author), Ponnuthurai Nagaratnam Suganthan (16003199) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513564341960704
author A.K. Malik (16003193)
author2 Ruobin Gao (16003195)
M.A. Ganaie (16003198)
M. Tanveer (1758181)
Ponnuthurai Nagaratnam Suganthan (16003199)
author2_role author
author
author
author
author_facet A.K. Malik (16003193)
Ruobin Gao (16003195)
M.A. Ganaie (16003198)
M. Tanveer (1758181)
Ponnuthurai Nagaratnam Suganthan (16003199)
author_role author
dc.creator.none.fl_str_mv A.K. Malik (16003193)
Ruobin Gao (16003195)
M.A. Ganaie (16003198)
M. Tanveer (1758181)
Ponnuthurai Nagaratnam Suganthan (16003199)
dc.date.none.fl_str_mv 2023-08-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.asoc.2023.110377
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Random_vector_functional_link_network_Recent_developments_applications_and_future_directions/23274407
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Machine learning
Software engineering
Random vector functional link (RVFL) network
Ensemble learning
Deep learning
Ensemble deep learning
Randomized neural networks (RNNs)
Single hidden layer feed forward neural network (SLFN)
Extreme learning machine (ELM)
dc.title.none.fl_str_mv Random vector functional link network: Recent developments, applications, and future directions
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it results in the issues of local minima, sensitivity to learning rate and slow convergence. To overcome these issues, randomization based neural networks such as random vector functional link (RVFL) network have been proposed. RVFL model has several characteristics such as fast training speed, direct links, simple architecture, and universal approximation capability, that make it a viable randomized neural network. This article presents the first comprehensive review of the evolution of RVFL model, which can serve as the extensive summary for the beginners as well as practitioners. We discuss the shallow RVFLs, ensemble RVFLs, deep RVFLs and ensemble deep RVFL models. The variations, improvements and applications of RVFL models are discussed in detail. Moreover, we discuss the different hyperparameter optimization techniques followed in the literature to improve the generalization performance of the RVFL model. Finally, we present potential future research directions/opportunities that can inspire the researchers to improve the RVFL’s architecture and learning algorithm further. </p> <h2>Other Information</h2> <p>Published in: Applied Soft Computing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/ </a> <br> See article on publisher's website: <a href="http://dx.doi.org/10.1016/j.asoc.2023.110377" target="_blank">http://dx.doi.org/10.1016/j.asoc.2023.110377</a> </p>
eu_rights_str_mv openAccess
id Manara2_d5c1253e9348569015584d7cbdaf9e58
identifier_str_mv 10.1016/j.asoc.2023.110377
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/23274407
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Random vector functional link network: Recent developments, applications, and future directionsA.K. Malik (16003193)Ruobin Gao (16003195)M.A. Ganaie (16003198)M. Tanveer (1758181)Ponnuthurai Nagaratnam Suganthan (16003199)Information and computing sciencesMachine learningSoftware engineeringRandom vector functional link (RVFL) networkEnsemble learningDeep learningEnsemble deep learningRandomized neural networks (RNNs)Single hidden layer feed forward neural network (SLFN)Extreme learning machine (ELM)<p>Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it results in the issues of local minima, sensitivity to learning rate and slow convergence. To overcome these issues, randomization based neural networks such as random vector functional link (RVFL) network have been proposed. RVFL model has several characteristics such as fast training speed, direct links, simple architecture, and universal approximation capability, that make it a viable randomized neural network. This article presents the first comprehensive review of the evolution of RVFL model, which can serve as the extensive summary for the beginners as well as practitioners. We discuss the shallow RVFLs, ensemble RVFLs, deep RVFLs and ensemble deep RVFL models. The variations, improvements and applications of RVFL models are discussed in detail. Moreover, we discuss the different hyperparameter optimization techniques followed in the literature to improve the generalization performance of the RVFL model. Finally, we present potential future research directions/opportunities that can inspire the researchers to improve the RVFL’s architecture and learning algorithm further. </p> <h2>Other Information</h2> <p>Published in: Applied Soft Computing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/ </a> <br> See article on publisher's website: <a href="http://dx.doi.org/10.1016/j.asoc.2023.110377" target="_blank">http://dx.doi.org/10.1016/j.asoc.2023.110377</a> </p>2023-08-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.asoc.2023.110377https://figshare.com/articles/journal_contribution/Random_vector_functional_link_network_Recent_developments_applications_and_future_directions/23274407CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/232744072023-08-01T00:00:00Z
spellingShingle Random vector functional link network: Recent developments, applications, and future directions
A.K. Malik (16003193)
Information and computing sciences
Machine learning
Software engineering
Random vector functional link (RVFL) network
Ensemble learning
Deep learning
Ensemble deep learning
Randomized neural networks (RNNs)
Single hidden layer feed forward neural network (SLFN)
Extreme learning machine (ELM)
status_str publishedVersion
title Random vector functional link network: Recent developments, applications, and future directions
title_full Random vector functional link network: Recent developments, applications, and future directions
title_fullStr Random vector functional link network: Recent developments, applications, and future directions
title_full_unstemmed Random vector functional link network: Recent developments, applications, and future directions
title_short Random vector functional link network: Recent developments, applications, and future directions
title_sort Random vector functional link network: Recent developments, applications, and future directions
topic Information and computing sciences
Machine learning
Software engineering
Random vector functional link (RVFL) network
Ensemble learning
Deep learning
Ensemble deep learning
Randomized neural networks (RNNs)
Single hidden layer feed forward neural network (SLFN)
Extreme learning machine (ELM)