Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCao, Haozhi
dc.description.abstractMulti-class classification is the classification task where separates samples into more than 2 classes. An image multi-class classifier is a mathematic model which can distinguish the category of pictures. One of the traditional models of image classifier is Convolutional Neural Network (CNN). However, the fully-connected layers of CNN usually contains significant number of parameters abasing the performance of CNN. As a result, in order to elevate the performance of CNN, it is necessary to reduce the parameters of fully-connected layers. In this project, inspired by previous improvement of Feedforward Neural Network, a theoretical CNN model with a binary decode output layer is proposed. To evaluate the accuracy as well as efficiency of this possible method, three different classification tasks are conducted and the test accuracy, training accuracy and training time are recorded independently. After analyzing the results above, it shows that binary decode approach can increase the test accuracy of CNN model and slightly accelerate the training process under some restricted conditions.en_US
dc.format.extent60 p.en_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen_US
dc.titleMulti-class classification using deep learningen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorMao Kezhien_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeBachelor of Engineering (Electrical and Electronic Engineering)en_US
dc.contributor.researchCentre for Intelligent Machinesen_US
item.fulltextWith Fulltext-
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
  Restricted Access
Main article1.49 MBAdobe PDFView/Open

Page view(s)

Updated on Nov 26, 2020

Download(s) 20

Updated on Nov 26, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.