Please use this identifier to cite or link to this item: https://hdl.handle.net/10321/3750
Title: Learning rate optimisation of an image processing deep convolutional neural network
Authors: Buthelezi, Sibusiso Blessing 
Issue Date: 2021
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.
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.
URI: https://hdl.handle.net/10321/3750
DOI: https://doi.org/10.51415/10321/3750
Appears in Collections:Theses and dissertations (Engineering and Built Environment)

Files in This Item:
File Description SizeFormat
ButheleziSB_2021.pdfThesis3.65 MBAdobe PDFView/Open
Show full item record

Page view(s)

303
checked on Jul 13, 2024

Download(s)

160
checked on Jul 13, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.