Automated design of the deep neural network pipeline

dc.contributor.authorGerber, Mia
dc.contributor.authorPillay, Nelishia
dc.contributor.emailu15016502@tuks.co.zaen_US
dc.date.accessioned2023-04-25T07:50:30Z
dc.date.available2023-04-25T07:50:30Z
dc.date.issued2022-11-29
dc.descriptionCorrection: Gerber M, Pillay N. Correction: Gerber, M.; Pillay, N. Automated Design of the Deep Neural Network Pipeline. Appl. Sci. 2022, 12, 12215. Applied Sciences. 2024; 14(5):1897. https://doi.org/10.3390/app14051897.
dc.description.abstractDeep neural networks have proven to be effective in various domains, especially in natural language processing and image processing. However, one of the challenges associated with using deep neural networks includes the long design time and expertise needed to apply these neural networks to a particular domain. The research presented in this paper investigates the automation of the design of the deep neural network pipeline to overcome this challenge. The deep learning pipeline includes identifying the preprocessing needed, the feature engineering technique, the neural network to use and the parameters for the neural network. A selection pertubative hyper-heuristic (SPHH) is used to automate the design pipeline. The study also examines the reusability of the generated pipeline. The effectiveness of transfer learning on the generated designs is also investigated. The proposed approach is evaluated for text processing—namely, sentiment analysis and spam detection— and image processing—namely, maize disease detection and oral lesion detection. The study revealed that the automated design of the deep neural network pipeline produces just as good, and in some cases better, performance compared to the manual design, with the automated design requiring less design time than the manual design. In the majority of instances, the design was not reusable; however, transfer learning achieved positive transfer of designs, with the performance being just as good or better than when transfer learning was not used.en_US
dc.description.departmentComputer Scienceen_US
dc.description.librarianam2023en_US
dc.description.sponsorshipThe National Research Foundation of South Africa.en_US
dc.description.urihttps://www.mdpi.com/journal/applscien_US
dc.identifier.citationGerber, M.; Pillay, N. Automated Design of the Deep Neural Network Pipeline. Applied Sciences 2022, 12, 12215. https://DOI.org/10.3390/app122312215.en_US
dc.identifier.issn2076-3417
dc.identifier.other10.3390/app122312215
dc.identifier.urihttp://hdl.handle.net/2263/90467
dc.language.isoenen_US
dc.publisherMDPIen_US
dc.rights© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.en_US
dc.subjectAutomated designen_US
dc.subjectDeep neural network pipelineen_US
dc.subjectTransfer learningen_US
dc.subjectSentiment analysisen_US
dc.subjectSpam detectionen_US
dc.subjectImage segmentationen_US
dc.subjectImage classificationen_US
dc.titleAutomated design of the deep neural network pipelineen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Gerber_Automated_2022.pdf
Size:
5.68 MB
Format:
Adobe Portable Document Format
Description:
Article
Loading...
Thumbnail Image
Name:
Gerber_Correction_2024.pdf
Size:
135.64 KB
Format:
Adobe Portable Document Format
Description:
Correction Notice

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description: