Artificial Neural Networks Training Acceleration Through Network Science Strategies
Book chapter
Authors | Lucia Cavallaro, Ovidiu Bagdasar, Pasquale De Meo, Giacomo Fiumara and 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. |
Keywords | Theoretical Computer Science; Software; Geometry and Topology; Artificial Neural Networks |
Year | 2020 |
Publisher | Springer Science and Business Media LLC |
ISSN | 1432-7643 |
1433-7479 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-40616-5_27 |
Web address (URL) | https://doi.org/10.1007/978-3-030-40616-5_27 |
File | File Access Level Open |
File | File Access Level Open |
File | File Access Level Open |
Publication dates | 2020 |
Publication process dates | |
Deposited | 17 Sep 2020, 07:58 |
Accepted | 24 Aug 2020 |
Rights | Attribution 4.0 International |
Journal | Soft Computing |
Contributors | University of Derby, University of Messina, Polo Universitario Annunziata, 98122, Messina, Italy and Free University of Bozen-Bolzano, Bolzano, Italy |
https://repository.derby.ac.uk/item/9363y/artificial-neural-networks-training-acceleration-through-network-science-strategies
Download files
File
license.txt | ||
File access level: Open |
license_rdf | ||
File access level: Open |
10.1007_s00500-020-05302-y.pdf | ||
File access level: Open |
68
total views22
total downloads3
views this month1
downloads this month