An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning
The choice of a good topology for a deep neural network is a complex task, essential for any deep learning project. This task normally demands knowledge from previous experience, as the higher amount of required computational resources makes trial and error approaches prohibitive. Evolutionary compu...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Journal of Electrical and Computer Engineering |
| Online Access: | http://dx.doi.org/10.1155/2019/3217542 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567798147055616 |
|---|---|
| author | Fernando Mattioli Daniel Caetano Alexandre Cardoso Eduardo Naves Edgard Lamounier |
| author_facet | Fernando Mattioli Daniel Caetano Alexandre Cardoso Eduardo Naves Edgard Lamounier |
| author_sort | Fernando Mattioli |
| collection | DOAJ |
| description | The choice of a good topology for a deep neural network is a complex task, essential for any deep learning project. This task normally demands knowledge from previous experience, as the higher amount of required computational resources makes trial and error approaches prohibitive. Evolutionary computation algorithms have shown success in many domains, by guiding the exploration of complex solution spaces in the direction of the best solutions, with minimal human intervention. In this sense, this work presents the use of genetic algorithms in deep neural networks topology selection. The evaluated algorithms were able to find competitive topologies while spending less computational resources when compared to state-of-the-art methods. |
| format | Article |
| id | doaj-art-693118ee3efb4812bb71f07c6f00303a |
| institution | Kabale University |
| issn | 2090-0147 2090-0155 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Electrical and Computer Engineering |
| spelling | doaj-art-693118ee3efb4812bb71f07c6f00303a2025-02-03T01:00:31ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552019-01-01201910.1155/2019/32175423217542An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep LearningFernando Mattioli0Daniel Caetano1Alexandre Cardoso2Eduardo Naves3Edgard Lamounier4Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, BrazilFaculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, BrazilFaculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, BrazilFaculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, BrazilFaculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG, BrazilThe choice of a good topology for a deep neural network is a complex task, essential for any deep learning project. This task normally demands knowledge from previous experience, as the higher amount of required computational resources makes trial and error approaches prohibitive. Evolutionary computation algorithms have shown success in many domains, by guiding the exploration of complex solution spaces in the direction of the best solutions, with minimal human intervention. In this sense, this work presents the use of genetic algorithms in deep neural networks topology selection. The evaluated algorithms were able to find competitive topologies while spending less computational resources when compared to state-of-the-art methods.http://dx.doi.org/10.1155/2019/3217542 |
| spellingShingle | Fernando Mattioli Daniel Caetano Alexandre Cardoso Eduardo Naves Edgard Lamounier An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning Journal of Electrical and Computer Engineering |
| title | An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning |
| title_full | An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning |
| title_fullStr | An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning |
| title_full_unstemmed | An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning |
| title_short | An Experiment on the Use of Genetic Algorithms for Topology Selection in Deep Learning |
| title_sort | experiment on the use of genetic algorithms for topology selection in deep learning |
| url | http://dx.doi.org/10.1155/2019/3217542 |
| work_keys_str_mv | AT fernandomattioli anexperimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT danielcaetano anexperimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT alexandrecardoso anexperimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT eduardonaves anexperimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT edgardlamounier anexperimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT fernandomattioli experimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT danielcaetano experimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT alexandrecardoso experimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT eduardonaves experimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning AT edgardlamounier experimentontheuseofgeneticalgorithmsfortopologyselectionindeeplearning |