Please use this identifier to cite or link to this item:
Title: Self-paced regularization in label distribution learning
Authors: Koh, Terence Kang Wei
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2019
Abstract: Label Distribution Learning is a learning paradigm which outputs a representation of how much each label describes the instance. Research into the paradigm involved machine learning algorithms but did not include deep learning as a possible alternative. Deep learning, a sub-discipline of machine learning, has seen a surge in popularity over the years. However, the process of training is time-consuming as it requires repetitively iterating over a huge training set. To combat this problem, we propose a combinatory method of self-paced regularization with deep learning, where the deep learning model is presented with training data with progressive levels of size, and by extension, difficulty. Experiment results were logged and compared to the traditional deep learning algorithm, as well as state-of-the-art machine learning algorithms.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
FYP report1.26 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 22, 2021


Updated on Jun 22, 2021

Google ScholarTM


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