Lucia Cavallaro
Artificial neural networks training acceleration through network science strategies
Cavallaro, Lucia; Bagdasar, Ovidiu; De Meo, Pasquale; Fiumara, Giacomo; Liotta, Antonio
Authors
Ovidiu Bagdasar
Pasquale De Meo
Giacomo Fiumara
Antonio Liotta
Abstract
The development of deep learning has led to a dramatic increase in the number of applications of artificial intelligence. However, the training of deeper neural networks for stable and accurate models translates into artificial neural networks (ANNs) that become unmanageable as the number of features increases. This work extends our earlier study where we explored the acceleration effects obtained by enforcing, in turn, scale freeness, small worldness, and sparsity during the ANN training process. The efficiency of that approach was confirmed by recent studies (conducted independently) where a million-node ANN was trained on non-specialized laptops. Encouraged by those results, our study is now focused on some tunable parameters, to pursue a further acceleration effect. We show that, although optimal parameter tuning is unfeasible, due to the high non-linearity of ANN problems, we can actually come up with a set of useful guidelines that lead to speed-ups in practical cases. We find that significant reductions in execution time can generally be achieved by setting the revised fraction parameter (ζ) to relatively low values.
Journal Article Type | Article |
---|---|
Online Publication Date | Sep 9, 2020 |
Publication Date | 2020-12 |
Deposit Date | Sep 16, 2020 |
Publicly Available Date | Sep 16, 2020 |
Journal | Soft Computing |
Print ISSN | 1432-7643 |
Electronic ISSN | 1433-7479 |
Publisher | BMC |
Peer Reviewed | Peer Reviewed |
Volume | 24 |
DOI | https://doi.org/10.1007/s00500-020-05302-y |
Keywords | Network science, Artificial neural networks, Multilayer perceptron, Revise phase |
Public URL | http://researchrepository.napier.ac.uk/Output/2685966 |
Files
Artificial Neural Networks Training Acceleration Through Network Science Strategies
(617 Kb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
This article is licensed under a Creative Commons Attribution 4.0 International License.
You might also like
The operator's response to P2P service demand
(2007)
Journal Article
Fast Millimeter Wave Assisted Beam-Steering for Passive Indoor Optical Wireless Networks
(2017)
Journal Article
Self-Learning Power Control in Wireless Sensor Networks
(2018)
Journal Article
Fusing Bluetooth Beacon Data with Wi-Fi Radiomaps for Improved Indoor Localization
(2017)
Journal Article
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search