Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/76943
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. | URI: | http://hdl.handle.net/10356/76943 | Schools: | School of Computer Science and Engineering | 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 | Size | Format | |
---|---|---|---|---|
FYP_v10.pdf Restricted Access | FYP report | 1.26 MB | Adobe PDF | View/Open |
Page view(s)
247
Updated on Mar 29, 2024
Download(s) 50
21
Updated on Mar 29, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.