Back to search
Georgia Institute of Technology
Combining Classification and Clustering Tasks to Categorize Known and Unknown Classes
Abstract
dc:description.abstractSince the past few years research has been directed towards the training of neural networks using unlabeled data or pairwise pseudo constraints known as unsupervised learning and semi-supervised learning respectively. In this thesis, we explored several methods to improve the performance of the current state-of-the-art algorithm for unsupervised learning called SCAN using semi-supervision from pairwise pseudo constraints.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Computer Science
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shabbir, Javeria
- Advisor dc:contributor.advisor
-
- Kira, Zsolt
- Committee members dc:contributor.committeemember
-
- Vela, Patricio A.
- Hoffman, Judy
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/70166