Online learning using deep random vector functional link network
Deep neural networks have shown their promise in recent years with their state-of-the-art results. Yet, backpropagation-based methods may suffer from time-consuming training process and catastrophic forgetting when performing online learning. In this work we attempt to curtail them by employing the...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174168 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-174168 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1741682024-03-22T15:40:46Z Online learning using deep random vector functional link network Shiva, Sreenivasan Hu, Minghui Suganthan, Ponnuthurai Nagaratnam School of Electrical and Electronic Engineering Engineering Extreme learning machine Online learning Deep neural networks have shown their promise in recent years with their state-of-the-art results. Yet, backpropagation-based methods may suffer from time-consuming training process and catastrophic forgetting when performing online learning. In this work we attempt to curtail them by employing the ensemble deep Random Vector Functional Link (edRVFL). As opposed to backpropagation-based neural networks that adjust weights iteratively, RVFL uses a closed-form solution method without iterative parameter learning. In addition, our approach allows the model to grow incrementally as new data is made available so that it can more resemble real-life learning scenarios. Our proposed online learning models were able to perform better on 72% of the datasets in the classification scenario and 80% of the datasets in the regression scenario, when compared to other available randomization-based online learning models in the literature. This is further supported by statistical comparisons which also show the stability of our network. Published version Open Access funding provided by the Qatar National Library, Qatar. 2024-03-18T07:29:27Z 2024-03-18T07:29:27Z 2023 Journal Article Shiva, S., Hu, M. & Suganthan, P. N. (2023). Online learning using deep random vector functional link network. Engineering Applications of Artificial Intelligence, 125, 106676-. https://dx.doi.org/10.1016/j.engappai.2023.106676 0952-1976 https://hdl.handle.net/10356/174168 10.1016/j.engappai.2023.106676 2-s2.0-85165041193 125 106676 en Engineering Applications of Artificial Intelligence © 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Extreme learning machine Online learning |
spellingShingle |
Engineering Extreme learning machine Online learning Shiva, Sreenivasan Hu, Minghui Suganthan, Ponnuthurai Nagaratnam Online learning using deep random vector functional link network |
description |
Deep neural networks have shown their promise in recent years with their state-of-the-art results. Yet, backpropagation-based methods may suffer from time-consuming training process and catastrophic forgetting when performing online learning. In this work we attempt to curtail them by employing the ensemble deep Random Vector Functional Link (edRVFL). As opposed to backpropagation-based neural networks that adjust weights iteratively, RVFL uses a closed-form solution method without iterative parameter learning. In addition, our approach allows the model to grow incrementally as new data is made available so that it can more resemble real-life learning scenarios. Our proposed online learning models were able to perform better on 72% of the datasets in the classification scenario and 80% of the datasets in the regression scenario, when compared to other available randomization-based online learning models in the literature. This is further supported by statistical comparisons which also show the stability of our network. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Shiva, Sreenivasan Hu, Minghui Suganthan, Ponnuthurai Nagaratnam |
format |
Article |
author |
Shiva, Sreenivasan Hu, Minghui Suganthan, Ponnuthurai Nagaratnam |
author_sort |
Shiva, Sreenivasan |
title |
Online learning using deep random vector functional link network |
title_short |
Online learning using deep random vector functional link network |
title_full |
Online learning using deep random vector functional link network |
title_fullStr |
Online learning using deep random vector functional link network |
title_full_unstemmed |
Online learning using deep random vector functional link network |
title_sort |
online learning using deep random vector functional link network |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/174168 |
_version_ |
1794549351372029952 |