Jeremy Pitt
WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets
Pitt, Jeremy; Burth Kurka, David; Hart, Emma; Cardoso, Rui P.
Abstract
In order to address scalability issues, which can be a challenge for Deep Learning methods, we propose Wide Learning of Diverse Architectures-a model that scales horizontally rather than vertically, enabling distributed learning. We propose a distributed version of a quality-diversity evolutionary algorithm (MAP-Elites) to evolve an architecturally diverse ensemble of shallow networks, each of which extracts a feature vector from the data. These features then become the input to a single shallow network which is optimised using gradient descent to solve a classification task. The technique is shown to perform well on two benchmark classification problems (MNIST and CIFAR). Additional experiments provide insight into the role that diversity plays in contributing to the performance of the repertoire.
Citation
Pitt, J., Burth Kurka, D., Hart, E., & Cardoso, R. P. (2021, April). WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets. Presented at 24th European Conference, EvoApplications 2021, Online
Presentation Conference Type | Conference Paper (published) |
---|---|
Conference Name | 24th European Conference, EvoApplications 2021 |
Start Date | Apr 7, 2021 |
End Date | Apr 9, 2021 |
Acceptance Date | Jan 20, 2021 |
Online Publication Date | Apr 1, 2021 |
Publication Date | 2021-04 |
Deposit Date | Mar 30, 2021 |
Publicly Available Date | Apr 2, 2022 |
Publisher | Springer |
Pages | 649-664 |
Series Title | Lecture Notes in Computer Science |
Series Number | 12694 |
Series ISSN | 1611-3349 |
Book Title | Applications of Evolutionary Computation: EvoApplications 2021 Proceedings |
ISBN | 978-3-030-72698-0 |
DOI | https://doi.org/10.1007/978-3-030-72699-7_41 |
Keywords | Diversity, MAP-elites, Machine Learning, Ensemble |
Public URL | http://researchrepository.napier.ac.uk/Output/2756732 |
Publisher URL | https://www.springer.com/gp/book/9783030726980 |
Files
WILDA: Wide Learning Of Diverse Architectures For Classification Of Large Datasets (accepted version)
(315 Kb)
PDF
You might also like
Advances in artificial immune systems
(2011)
Journal Article
On Clonal Selection.
(2011)
Journal Article
Structure versus function: a topological perspective on immune networks
(2009)
Journal Article
How affinity influences tolerance in an idiotypic network.
(2007)
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