Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/163999
Title: Modular learning of convolutional neural networks
Authors: Wang, Jinhua
Keywords: Engineering::Electrical and electronic engineering
Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Wang, J. (2022). Modular learning of convolutional neural networks. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/163999
Project: ISM-DISS-03097 
Abstract: In recent years, a wide variety of network structures and training methods have been proposed for deep learning. However, the underlying mechanism of a deep network is not fully understood, which is considered as a black box system. The layer-wise learning method was proposed a decade ago, but now it is rarely used due to the trade-off in performance as compared to the standard end-to-end learning. Recently, layer-wise learning has been considered for application in interpretable or analytical neural networks. Therefore, a key target is to improve the performance of the layer-wise learning. In this dissertation, a modular deep learning method is developed on the basis of classical layer-wise learning. In addition, the network performance is further improved by proposing epoch-wise learning on the basis of modular deep learning. Through the case studies using several common datasets, the proposed approaches are compared with the traditional layer-wise learning method in terms of performance.
URI: https://hdl.handle.net/10356/163999
Schools: School of Electrical and Electronic Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Modular_Learning_of_Convolutional_Neural_Networks.pdf
  Restricted Access
2.3 MBAdobe PDFView/Open

Page view(s)

218
Updated on Apr 18, 2024

Download(s)

5
Updated on Apr 18, 2024

Google ScholarTM

Check

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