Random vector functional link neural network based deep learning for regression
The deep RVFLs are inspired by the principles of the Random Vector Functional Link (RVFL) neural network. Like RVFL, the weights of the hidden layers of the deep RVFLs (dRVFL and edRVFL) are stochastically generated within a suitable range and kept constant throughout the training. In this paper, we...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/140217 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-140217 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1402172023-07-07T18:51:44Z Random vector functional link neural network based deep learning for regression Chion, Jet Herng Ponnuthurai Nagaratnam Suganthan School of Electrical and Electronic Engineering epnsugan@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering The deep RVFLs are inspired by the principles of the Random Vector Functional Link (RVFL) neural network. Like RVFL, the weights of the hidden layers of the deep RVFLs (dRVFL and edRVFL) are stochastically generated within a suitable range and kept constant throughout the training. In this paper, we test and evaluate the performances of the recently proposed deep RVFLs neural networks on regression problems. Through the comprehensive evaluation on 29 different UCI datasets, we show that the performances of both dRVFL and edRVFL are significantly better than the RVFL variant (OPE-RVFL) in [1] and on par with backpropagation based Deep Neural Network. Furthermore, we identify Sigmoid as the most suitable activation function for regression tasks. Finally, we propose three new deep RVFLs variants (Deep Boosted dRVFL, edRVFL+ and Two-stage edRVFL+R) which show significant improvement over the vanilla deep RVFLs. Two-stage edRVFL+R is identified as the best performing algorithm among the three newly proposed variants as it performs better than the deep neural network in 22 out of the 29 UCI datasets. The robustness of the Two-stage edRVFL+R is further confirmed by the fact that it outperforms another method (Parallel metaheuristic-ensemble of heterogeneous feedforward neural networks ) proposed in [2] by a large margin in 11 out of 14 selected datasets. Bachelor of Engineering (Electrical and Electronic Engineering) 2020-05-27T07:04:08Z 2020-05-27T07:04:08Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/140217 en A1131-191 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering Chion, Jet Herng Random vector functional link neural network based deep learning for regression |
description |
The deep RVFLs are inspired by the principles of the Random Vector Functional Link (RVFL) neural network. Like RVFL, the weights of the hidden layers of the deep RVFLs (dRVFL and edRVFL) are stochastically generated within a suitable range and kept constant throughout the training. In this paper, we test and evaluate the performances of the recently proposed deep RVFLs neural networks on regression problems. Through the comprehensive evaluation on 29 different UCI datasets, we show that the performances of both dRVFL and edRVFL are significantly better than the RVFL variant (OPE-RVFL) in [1] and on par with backpropagation based Deep Neural Network. Furthermore, we identify Sigmoid as the most suitable activation function for regression tasks. Finally, we propose three new deep RVFLs variants (Deep Boosted dRVFL, edRVFL+ and Two-stage edRVFL+R) which show significant improvement over the vanilla deep RVFLs. Two-stage edRVFL+R is identified as the best performing algorithm among the three newly proposed variants as it performs better than the deep neural network in 22 out of the 29 UCI datasets. The robustness of the Two-stage edRVFL+R is further confirmed by the fact that it outperforms another method (Parallel metaheuristic-ensemble of heterogeneous feedforward neural networks ) proposed in [2] by a large margin in 11 out of 14 selected datasets. |
author2 |
Ponnuthurai Nagaratnam Suganthan |
author_facet |
Ponnuthurai Nagaratnam Suganthan Chion, Jet Herng |
format |
Final Year Project |
author |
Chion, Jet Herng |
author_sort |
Chion, Jet Herng |
title |
Random vector functional link neural network based deep learning for regression |
title_short |
Random vector functional link neural network based deep learning for regression |
title_full |
Random vector functional link neural network based deep learning for regression |
title_fullStr |
Random vector functional link neural network based deep learning for regression |
title_full_unstemmed |
Random vector functional link neural network based deep learning for regression |
title_sort |
random vector functional link neural network based deep learning for regression |
publisher |
Nanyang Technological University |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/140217 |
_version_ |
1772825221345050624 |