Please use this identifier to cite or link to this item:
https://hdl.handle.net/10321/3750
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Reddy, Seren | - |
dc.contributor.advisor | Twala, Bhekisipho | - |
dc.contributor.author | Buthelezi, Sibusiso Blessing | en_US |
dc.date.accessioned | 2021-12-09T16:34:54Z | - |
dc.date.available | 2021-12-09T16:34:54Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | https://hdl.handle.net/10321/3750 | - |
dc.description | A dissertation submitted in fulfilment of the requirements for the degree of Master of Engineering Department of Electronics and Computer Engineering, Faculty of Engineering and the Built Environment, Durban University of Technology, 2021. | en_US |
dc.description.abstract | The major contribution of this dissertation is the proposal of the use of mathematical models to identify an optimal learning rate for an image processing deep convolutional neural network (DCNN). This model is derived from a nonlinear regression relationship between the learning rate and the accuracy of a test DCNN model. This relationship is meant to (A) resolve the problem of arbitrarily selecting the initial learning rate (B) reduce computational resource requirement and (C) reduce training instabilities. An algorithm is developed to analyse an inputted DCNN model and subsequently render output parameters that may be used to aid in the selection of an OLR. The benefit of an OLR includes improved training stability and reduced computational resources. The results rendered by the OLR algorithm proposes that an optimal learning rate improves model performance; this is described by the test model average accuracy of 91%. Furthermore, a model validation graph is also extrapolated. which will illustrate the mathematical model accuracy and the region of interest (ROI). The ROI defines the region in the learning rate spectrum with a positive effect on model performance. | en_US |
dc.format.extent | 97 p | en_US |
dc.language.iso | en | en_US |
dc.subject.lcsh | Image processing | en_US |
dc.subject.lcsh | Mathematical models | en_US |
dc.subject.lcsh | Mathematical optimization | en_US |
dc.subject.lcsh | Neural networks (Computer science) | en_US |
dc.title | Learning rate optimisation of an image processing deep convolutional neural network | en_US |
dc.type | Thesis | en_US |
dc.description.level | M | en_US |
dc.identifier.doi | https://doi.org/10.51415/10321/3750 | - |
local.sdg | SDG03 | - |
item.languageiso639-1 | en | - |
item.openairetype | Thesis | - |
item.cerifentitytype | Publications | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
Appears in Collections: | Theses and dissertations (Engineering and Built Environment) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ButheleziSB_2021.pdf | Thesis | 3.65 MB | Adobe PDF | View/Open |
Page view(s)
359
checked on Dec 22, 2024
Download(s)
182
checked on Dec 22, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.