Random vector functional link neural network based ensemble deep learning
In this paper, we propose deep learning frameworks based on the randomized neural network. Inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated w...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161420 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-161420 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1614202022-08-31T06:22:01Z Random vector functional link neural network based ensemble deep learning Shi, Qiushi Katuwal, Rakesh Suganthan, Ponnuthurai Nagaratnam Tanveer, M. School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Random Vector Functional Link Ensemble Deep Learning In this paper, we propose deep learning frameworks based on the randomized neural network. Inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated within a suitable range and kept fixed while the output weights are computed using the closed-form solution as in a standard RVFL network. We also propose an ensemble deep network (edRVFL) that can be regarded as a marriage of ensemble learning with deep learning. Unlike traditional ensembling approaches that require training several models independently from scratch, edRVFL is obtained by training a single dRVFL network once. Both dRVFL and edRVFL frameworks are generic and can be used with any RVFL variant. To illustrate this, we integrate the deep learning RVFL networks with a recently proposed sparse pre-trained RVFL (SP-RVFL). Experiments on 46 tabular UCI classification datasets and 12 sparse datasets demonstrate that the proposed deep RVFL networks outperform state-of-the-art deep feed-forward neural networks (FNNs). 2022-08-31T06:22:01Z 2022-08-31T06:22:01Z 2021 Journal Article Shi, Q., Katuwal, R., Suganthan, P. N. & Tanveer, M. (2021). Random vector functional link neural network based ensemble deep learning. Pattern Recognition, 117, 107978-. https://dx.doi.org/10.1016/j.patcog.2021.107978 0031-3203 https://hdl.handle.net/10356/161420 10.1016/j.patcog.2021.107978 2-s2.0-85104699070 117 107978 en Pattern Recognition © 2021 Elsevier Ltd. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Random Vector Functional Link Ensemble Deep Learning |
spellingShingle |
Engineering::Electrical and electronic engineering Random Vector Functional Link Ensemble Deep Learning Shi, Qiushi Katuwal, Rakesh Suganthan, Ponnuthurai Nagaratnam Tanveer, M. Random vector functional link neural network based ensemble deep learning |
description |
In this paper, we propose deep learning frameworks based on the randomized neural network. Inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated within a suitable range and kept fixed while the output weights are computed using the closed-form solution as in a standard RVFL network. We also propose an ensemble deep network (edRVFL) that can be regarded as a marriage of ensemble learning with deep learning. Unlike traditional ensembling approaches that require training several models independently from scratch, edRVFL is obtained by training a single dRVFL network once. Both dRVFL and edRVFL frameworks are generic and can be used with any RVFL variant. To illustrate this, we integrate the deep learning RVFL networks with a recently proposed sparse pre-trained RVFL (SP-RVFL). Experiments on 46 tabular UCI classification datasets and 12 sparse datasets demonstrate that the proposed deep RVFL networks outperform state-of-the-art deep feed-forward neural networks (FNNs). |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Shi, Qiushi Katuwal, Rakesh Suganthan, Ponnuthurai Nagaratnam Tanveer, M. |
format |
Article |
author |
Shi, Qiushi Katuwal, Rakesh Suganthan, Ponnuthurai Nagaratnam Tanveer, M. |
author_sort |
Shi, Qiushi |
title |
Random vector functional link neural network based ensemble deep learning |
title_short |
Random vector functional link neural network based ensemble deep learning |
title_full |
Random vector functional link neural network based ensemble deep learning |
title_fullStr |
Random vector functional link neural network based ensemble deep learning |
title_full_unstemmed |
Random vector functional link neural network based ensemble deep learning |
title_sort |
random vector functional link neural network based ensemble deep learning |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/161420 |
_version_ |
1743119493070061568 |